diff --git a/.codex b/.codex deleted file mode 100644 index e69de29..0000000 diff --git a/AGENTS.md b/AGENTS.md index 6a3d1e8..401f962 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -8,12 +8,10 @@ This file provides guidelines for codex agents contributing to the Sortana proje - `modules/`: Contains reusable JavaScript modules such as `AiClassifier.js`, `defaultParams.js` and `themeUtils.js`. - `options/`: The options page HTML, JavaScript and bundled Bulma CSS (v1.0.3). -- `details.html` and `details.js`: View classification evidence and clear cache for a message. +- `details.html` and `details.js`: View AI reasoning and clear cache for a message. - `resources/`: Images and other static files. +- `prompt_templates/`: Prompt template files for the AI service. - `build-xpi.ps1`: PowerShell script to package the extension. -- `build-xpi.sh`: Bash script to package the extension. -- `resources/svg2img.ps1`: PowerShell script to regenerate themed PNG icons from SVGs. -- `resources/svg2img.sh`: Bash script to regenerate themed PNG icons from SVGs. ## Coding Style @@ -30,65 +28,7 @@ This file provides guidelines for codex agents contributing to the Sortana proje ## Testing -Run the dependency-free suite with Node.js 22 or newer: `node --test tests/*.test.mjs`. -The tests mock extension storage, HTTP responses, and Thunderbird rule execution. -Manual verification in Thunderbird is still required for UI and real-server integration. -Do **not** run the `ps1` build script or the SVG processing script. - -## Endpoint Notes - -Sortana supports `apiType: "chat-completions"` (default) and `"systemone"`. -Plain adapter modules under `modules/backends/` own request construction and response -validation; `AiClassifier` owns shared transport, configuration snapshots, threshold -policy, and caching. The stored endpoint is a base URL. Normalization accepts `/v1` -and recognized full API paths, preserves proxy prefixes, and defaults to HTTPS -when no scheme is supplied. Model discovery uses `/v1/models`; **None** omits `model`. -Bearer authentication is optional for both APIs. Organization/project headers are -sent only for Chat Completions. - -Chat Completions sends system/user messages and extracts the last JSON object from -`choices[0].message.content`, requiring a `match` or `matched` boolean. SystemOne -sends prepared email text as `state` with `noul` questions identified by stable -`rule_` IDs. The single-question API still uses `match` for backward -compatibility and cache fingerprinting. Every requested answer must have type -`noul` and a finite numeric probability in `[0, 1]`; response order is irrelevant. -No chat generation parameters or system prompt are sent to SystemOne. - -The global `decisionThreshold` defaults to 0.5; optional rule-level -`decisionThreshold` overrides it. UI percentages are stored as numbers in `[0, 1]`. -Matching uses `probability >= threshold` before display rounding. Details displays -probabilities in a progress bar with the percentage inside; threshold and model -appear in its tooltip. Results use the current threshold, never fabricated reasoning or action -history. No secondary model calls are made. - -`classify()` returns structured evidence; `classifyText()` remains a boolean wrapper. -Failures throw and are never cached. HTTP errors include the request URL and -JSON server error message when available; SystemOne 404 errors suggest checking -the running server build and decision-model support. The rule runner stops that email, reports the -error, and continues the next queued email. Snapshot settings and rules per email. -`inputCharacterLimit` replaces coupling input truncation to output `max_tokens`; -it applies with aggressive reduction and migrates from the old effective limit. - -### SystemOne batching - -`systemOneProcessAll` defaults to true; `systemOneBatchSize` defaults to 8 and must -be a positive safe integer. Only SystemOne shows these controls. The numeric input -is disabled while Process all is enabled, retaining its value. Include both in -settings import/export, startup loading, live updates, and per-email snapshots. - -`classifyRules()` is a lazy ordered async iterator over precomputed candidate keys. -Chat requests stay sequential. SystemOne batches the next N unique uncached keys -(or all), sends state once, validates the whole response, and persists one batch -of evidence before yielding ordered results. Per-rule thresholds remain independent. -Do not change existing cache keys or include batch settings in their fingerprint. -Prepare eligibility and keys before actions, using the existing initial mail metadata. - -Stop-after-match ends action iteration and prevents further requests; already -computed later answers remain cached. A malformed answer fails its entire batch: -no partial cache writes or new actions. Keep cache-generation guards for imports -and clearing during inference. No automatic splitting or retries. Tests in -`tests/batching.test.mjs` cover batching, cache reuse, failure atomicity, and actual -rule-runner stop behavior with the real classifier. +There are currently no automated tests for this project. If you add tests in the future, specify the commands to run them here. For now, verification must happen manually in Thunderbird. Do **not** run the `ps1` build script or the SVG processing script. ## Documentation @@ -122,26 +62,15 @@ text extracted from all text parts. ### Cache Strategy -`aiCache` persists version 2 inference evidence. Keys are -`v2::`. -Include backend, endpoint, model, effective request parameters and preprocessing; -exclude secrets, actions and thresholds. Recompute SystemOne matches from cached -probability and current thresholds without automatically executing actions. -Entries retain a hashed message identifier for clearing across configurations. -Version 4.0.0 intentionally breaks legacy cache compatibility: legacy caches -(including `aiReasonCache`) are invalidated because their inference -configuration is unknown. Import/export validates versioned evidence; storage -changes refresh the running cache. Maintenance uses `sortana:getCacheSize` to -count validated entries in the background classifier, rather than raw storage keys. -Full restoration requires matching settings and rules as well as cache evidence; -`tests/cacheRestore.test.mjs` exercises export/reinstall/import through the actual -storage and Details handlers, including changed numeric Thunderbird message IDs. Clearing/importing during inference prevents -that in-flight result from repopulating the replaced cache. +`aiCache` persists classification results. Each key is the SHA‑256 hex of +`"|"` and maps to an object with `matched` and `reason` +properties. Any legacy `aiReasonCache` data is merged into `aiCache` the first +time the add-on loads after an update. ### Icon Set Usage Toolbar and menu icons reside under `resources/img` and are provided in 16, 32 and 64 pixel variants. When changing these icons, pass a dictionary mapping the sizes to the paths in `browserAction.setIcon` or `messageDisplayAction.setIcon`. -Use `resources/svg2img.ps1` on Windows or `resources/svg2img.sh` on Linux to -regenerate PNGs from the SVG sources. +Use `resources/svg2img.ps1` to regenerate PNGs from the SVG sources. + diff --git a/README.md b/README.md index 999d826..3853127 100644 --- a/README.md +++ b/README.md @@ -4,145 +4,47 @@ Sortana is an experimental Thunderbird add-on that integrates an AI-powered filter rule. It allows you to classify email messages by sending their contents to a configurable -HTTP endpoint. Choose **Chat Completions** for an OpenAI-compatible -`/v1/chat/completions` service or **SystemOne** for decision models served through -`/v1/systemone`. Chat Completions returns a match boolean and textual explanation; -SystemOne returns a match probability, compared against a configurable threshold. -The options page stores a base URL and shows the resolved request URL. +HTTP endpoint. The endpoint should respond with JSON indicating whether the +message meets a specified criterion. ## Features -- **Configurable endpoint** – set the classification service base URL on the options page. -- **Model selection** – load available models from the endpoint and choose one (or omit the model field). -- **Optional OpenAI auth headers** – provide an API key plus optional organization/project headers when needed. -- **Custom system prompts** – tailor the instructions sent as the system message for more precise results. +- **Configurable endpoint** – set the classification service URL on the options page. +- **Prompt templates** – choose between several model formats or provide your own custom template. +- **Custom system prompts** – tailor the instructions sent to the model for more precise results. - **Persistent result caching** – classification results and reasoning are saved to disk so messages aren't re-evaluated across restarts. -- **Advanced parameters (Chat Completions)** – tune generation settings like temperature, top‑p and more from the options page. - Provider-specific advanced fields are forwarded as configured and may be rejected by strict OpenAI endpoints. +- **Advanced parameters** – tune generation settings like temperature, top‑p and more from the options page. - **Markdown conversion** – optionally convert HTML bodies to Markdown before sending them to the AI service. - **Debug logging** – optional colorized logs help troubleshoot interactions with the AI service. -- **Debug tab** – view the last request payload and a diff between the unaltered message text and the final prompt. - **Light/Dark themes** – automatically match Thunderbird's appearance with optional manual override. - **Automatic rules** – create rules that tag, move, copy, forward, reply, delete, archive, mark read/unread or flag/unflag messages based on AI classification. Rules can optionally apply only to unread messages and can ignore messages outside a chosen age range. - **Rule ordering** – drag rules to prioritize them and optionally stop processing after a match. - **Rule enable/disable** – temporarily turn a rule off without removing it. - **Account & folder filters** – limit rules to specific accounts or folders. - **Context menu** – apply AI rules from the message list or the message display action button. -- **Status icons** – toolbar icons show when classification is in progress and briefly display success states. If a failure occurs the icon turns red briefly before returning to normal. -- **Error notification** – failed classification displays a notification in Thunderbird. -- **Session error log** – the Errors tab (visible only when errors occur) shows errors recorded since the last add-on start. -- **View results** – inspect chat explanations or SystemOne probabilities and thresholds in the Details popup. +- **Status icons** – toolbar icons show when classification is in progress and briefly display success states. If a failure occurs the icon turns red until you dismiss the notification. +- **Error notification** – failed classification displays a notification with a button to clear the error and reset the icon. +- **View reasoning** – inspect why rules matched via the Details popup. - **Cache management** – clear cached results from the context menu or options page. - **Queue & timing stats** – monitor processing time on the Maintenance tab. -- **Packaging scripts** – `build-xpi.ps1` (PowerShell) or `build-xpi.sh` (bash) build an XPI ready for installation. -- **Icon generation scripts** – `resources/svg2img.ps1` (PowerShell) or `resources/svg2img.sh` (bash) regenerate themed PNG icons from the SVG sources. +- **Packaging script** – `build-xpi.ps1` builds an XPI ready for installation. - **Maintenance tab** – view rule counts, cache entries and clear cached results from the options page. ### Cache Storage -Classification results are stored under `aiCache` using version 2 entries. Keys -combine a hashed Message-ID with a fingerprint of the criterion, backend, -endpoint, selected model, effective request settings, and preprocessing settings. -Credentials and thresholds are excluded. SystemOne probabilities are retained at -full precision; changing a threshold reuses the evidence without another request. -Changing inference settings requires a fresh classification. If the model behind -an unchanged server/model alias changes, clear the cache manually. - -**Version 4.0.0 upgrade note:** legacy cache entries and `aiReasonCache` are discarded because -they do not identify the inference configuration. Settings and rules are retained. -Imported legacy caches are also discarded. To restore cached Details after reinstalling, -export and import **Settings, Rules, and Cache** together: lookups require the -original criterion and matching inference settings. Import refreshes the running -classifier immediately; Maintenance counts its validated, loaded entries. A cache-only -import will not recreate rules or settings. Clearing a message's cache removes its -entries across rules and configurations. - -### SystemOne with llama-server - -Use a llama.cpp build supporting `/v1/systemone` and a compatible decision GGUF; -older builds and ordinary chat models cannot serve this API. A 404 with -`File Not Found` from `/v1/systemone` indicates the route is unavailable: check -the running server build and any reverse-proxy routing. Loading a decision GGUF -alone does not add this route to an older server. For example: - -```sh -llama-server -hf ggml-org/Laya-GGUF -``` - -1. Select **SystemOne** in Settings and set the endpoint to `http://127.0.0.1:8080` - (or your server's address). Refresh models and select one, or choose **None** - for a single loaded model. Router deployments require the appropriate model ID. -2. Set the default match probability threshold (initially **50%**). Each rule has - an optional percentage override; leave it blank to inherit the default. -3. Apply rules normally. Each uncached criterion becomes a `noul` question. A rule - matches when the unrounded probability is **greater than or equal to** its - effective threshold. For example, 80% matches an 80% threshold. -4. Open Details to see a probability bar with the percentage inside. Hover over - the bar to see the current threshold and model. This is the - result under current settings, not an action history. Changing thresholds does - not automatically rerun actions. Decision models provide no textual explanation; - no second model is called to invent one. Use Chat Completions for explanations. - -**SystemOne batching:** **Process all** is enabled by default and sends all eligible, -uncached criteria for an email in one request, with the email state included once. -Turn it off to set **Rules per request** (initially 8); use 1 for sequential -requests. The number is retained while disabled. These controls apply only to -SystemOne; Chat Completions continues processing one rule per request. - -Cached rules consume no batch capacity, and identical criteria share a question -while retaining their individual thresholds. Actions execute in rule order and -honor stop-after-match. A batch can evaluate later rules whose actions are then -skipped; their probabilities remain available in Details. No further batches are -requested after stopping. Changing batch settings preserves existing cached results. - -If any requested answer is missing or invalid, the entire batch fails without -caching its new answers or executing their actions. Previously completed actions -remain applied. Sortana does not automatically retry or split rejected batches; -if the server rejects a large request, disable Process all and reduce Rules per -request. Limits and performance depend on the server and model. - -Probabilities are model estimates, not guaranteed accuracy. Evaluate thresholds -against representative labeled emails, including long messages and attachments. -SystemOne uses the existing text extraction and attachment summaries; it does not -send attachment binaries or images. Chat prompts and generation settings remain -saved but are inactive for SystemOne. Optional Bearer authentication works with -both APIs; organization/project headers apply only to Chat Completions. - -**Input character limit** applies when aggressive reduction is enabled, independently -of maximum output tokens. Existing installations inherit their previous effective -character limit; the default is 3686. Character counts do not guarantee that input -fits a model's token context or llama-server batch limits. Leave room for question -instructions and configure the server for the chosen model. - -A request or response-parsing failure stops the remaining rules for that email, -records an error, and allows the queue to continue with the next email. Failed -results are never cached. Actions already completed are not rolled back. - -Upstream: [llama-server SystemOne documentation](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md#typesafe-compatible-api-endpoints). - -### Verification - -Run the dependency-free tests with Node.js 22 or newer: - -```sh -node --test tests/*.test.mjs -``` - -Tests cover adapters, thresholds, URLs, settings validation, cache migration and -reuse, request failures, per-email snapshots, and queue behavior with mocked -Thunderbird services. Manual acceptance testing in Thunderbird should verify both -API types, model discovery, rule overrides and ordering, import/export, cache -clearing, Details, and stop-after-match against a running server. +Classification results are stored under the `aiCache` key in extension storage. +Each entry maps a SHA‑256 hash of `"|"` to an object +containing `matched` and `reason` fields. Older installations with a separate +`aiReasonCache` will be migrated automatically on startup. ## Architecture Overview -Sortana is implemented entirely with documented MailExtension/WebExtension APIs. No custom experiment code or Thunderbird-internal fallback paths are required: +Sortana is implemented entirely with standard WebExtension scripts—no custom experiment code is required: - `background.js` loads saved settings, manages the classification queue and listens for new messages. -- `modules/AiClassifier.js` shares transport, threshold policy, and cache handling; - `modules/backends/` contains the Chat Completions and SystemOne adapters. +- `modules/AiClassifier.js` implements the classification logic and cache handling. - `options/` contains the HTML and JavaScript for configuring the endpoint and rules. -- `details.html` / `details.js` present cached classification evidence for a message. +- `details.html` / `details.js` present cached reasoning for a message. - `_locales/` holds localized strings used throughout the UI. ### Key Files @@ -153,29 +55,23 @@ Sortana is implemented entirely with documented MailExtension/WebExtension APIs. | `background.js` | Startup tasks and classification queue management. | | `modules/AiClassifier.js` | Core classification logic and cache handling. | | `options/options.html` and `options.js` | Endpoint and rule configuration UI. | -| `details.html` and `details.js` | View stored classification evidence for a message. | +| `details.html` and `details.js` | View stored reasoning for a message. | | `logger.js` | Colorized logging with optional debug mode. | ## Building -1. Ensure PowerShell is available on Windows or bash, `python3`, and Inkscape are - available on Linux. +1. Ensure PowerShell is available (for Windows) or adapt the script for other + environments. 2. The Bulma stylesheet (v1.0.3) is already included as `options/bulma.css`. -3. Run `powershell ./build-xpi.ps1` or `./build-xpi.sh` from the repository root. - The script reads the version from `manifest.json` and creates an XPI in the - `release` folder. +3. Run `powershell ./build-xpi.ps1` from the repository root. The script reads + the version from `manifest.json` and creates an XPI in the `release` folder. 4. Install the generated XPI in Thunderbird via the Add-ons Manager. During development you can also load the directory as a temporary add-on. -5. To regenerate PNG icons from the SVG sources, run `resources/svg2img.ps1` on - Windows or `./resources/svg2img.sh` on Linux. +5. To regenerate PNG icons from the SVG sources, run `resources/svg2img.ps1`. ## Usage -1. Open the add-on's options and set the base URL of your classification service - (Sortana appends the path for the selected API type). Use the Model dropdown to load - `/v1/models` and select a model or choose **None** to omit the `model` field. - Advanced settings include optional API key, organization, and project headers - for OpenAI-hosted endpoints. +1. Open the add-on's options and set the URL of your classification service. 2. Use the **Classification Rules** section to add a criterion and optional actions such as tagging, moving, copying, forwarding, replying, deleting or archiving a message when it matches. Drag rules to @@ -188,7 +84,7 @@ Sortana is implemented entirely with documented MailExtension/WebExtension APIs. open a compose window using the account that received the message. 3. Save your settings. New mail will be evaluated automatically using the configured rules. -4. If the toolbar icon shows a red X, it will clear after a few seconds. Open the Errors tab in Options to review the latest failures. +4. If the toolbar icon shows a red X, click the notification's **Dismiss** button to clear the error. ### Example Filters @@ -244,8 +140,6 @@ uses the following third party libraries: - MIT License - [turndown v7.2.0](https://github.com/mixmark-io/turndown/tree/v7.2.0) - MIT License -- [diff](https://github.com/google/diff-match-patch/blob/62f2e689f498f9c92dbc588c58750addec9b1654/javascript/diff_match_patch_uncompressed.js) - - Apache-2.0 license ## License @@ -261,3 +155,4 @@ how Thunderbird's WebExtension and experiment APIs can be extended. Their code provided invaluable guidance during development. - Icons from [cc0-icons.jonh.eu](https://cc0-icons.jonh.eu/) are used under the CC0 license. + diff --git a/_locales/en-US/messages.json b/_locales/en-US/messages.json index 472956a..983bb86 100644 --- a/_locales/en-US/messages.json +++ b/_locales/en-US/messages.json @@ -4,15 +4,21 @@ "doesntMatch": { "message": "doesn't match" }, "options.title": { "message": "AI Filter Options" }, "options.endpoint": { "message": "Endpoint" }, + "options.template": { "message": "Prompt template" }, + "options.customTemplate": { "message": "Custom template" }, "options.systemInstructions": { "message": "System instructions" }, "options.reset": { "message": "Reset to default" }, + "options.placeholders": { "message": "Placeholders: {{system}}, {{email}}, {{query}}" }, + "template.openai": { "message": "OpenAI / ChatML" }, + "template.qwen": { "message": "Qwen" }, + "template.mistral": { "message": "Mistral" }, + "template.custom": { "message": "Custom" }, "options.save": { "message": "Save" }, "options.debugLogging": { "message": "Enable debug logging" }, "options.htmlToMarkdown": { "message": "Convert HTML body to Markdown" }, "options.stripUrlParams": { "message": "Remove URL tracking parameters" }, "options.altTextImages": { "message": "Replace images with alt text" }, - "options.collapseWhitespace": { "message": "Collapse long whitespace" }, - "options.tokenReduction": { "message": "Aggressive token reduction" } + "options.collapseWhitespace": { "message": "Collapse long whitespace" } ,"action.read": { "message": "read" } ,"action.flag": { "message": "flag" } ,"action.copy": { "message": "copy" } diff --git a/ai-filter.sln b/ai-filter.sln index 52e32fe..57705eb 100644 --- a/ai-filter.sln +++ b/ai-filter.sln @@ -39,6 +39,13 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "en-US", "en-US", "{8BEA7793 _locales\en-US\messages.json = _locales\en-US\messages.json EndProjectSection EndProject +Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "prompt_templates", "prompt_templates", "{86516D53-50D4-4FE2-9D8A-977A8F5EBDBD}" + ProjectSection(SolutionItems) = preProject + prompt_templates\mistral.txt = prompt_templates\mistral.txt + prompt_templates\openai.txt = prompt_templates\openai.txt + prompt_templates\qwen.txt = prompt_templates\qwen.txt + EndProjectSection +EndProject Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "resources", "resources", "{68A87938-5C2B-49F5-8AAA-8A34FBBFD854}" ProjectSection(SolutionItems) = preProject resources\svg2img.ps1 = resources\svg2img.ps1 @@ -101,7 +108,6 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "img", "img", "{F266602F-175 EndProject Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "js", "js", "{21D2A42C-3F85-465C-9141-C106AFD92B68}" ProjectSection(SolutionItems) = preProject - resources\js\diff_match_patch_uncompressed.js = resources\js\diff_match_patch_uncompressed.js resources\js\turndown.js = resources\js\turndown.js EndProjectSection EndProject diff --git a/background.js b/background.js index 602fe1f..06683e2 100644 --- a/background.js +++ b/background.js @@ -19,7 +19,6 @@ let queue = Promise.resolve(); let queuedCount = 0; let processing = false; let iconTimer = null; -let errorTimer = null; let timingStats = { count: 0, mean: 0, m2: 0, total: 0, last: -1 }; let currentStart = 0; let logGetTiming = true; @@ -27,17 +26,12 @@ let htmlToMarkdown = false; let stripUrlParams = false; let altTextImages = false; let collapseWhitespace = false; -let tokenReduction = false; let TurndownService = null; let userTheme = 'auto'; let currentTheme = 'light'; let detectSystemTheme; let errorPending = false; -let errorLog = []; -let showDebugTab = false; const ERROR_NOTIFICATION_ID = 'sortana-error'; -const ERROR_ICON_TIMEOUT = 4500; -const MAX_ERROR_LOG = 50; function normalizeRules(rules) { return Array.isArray(rules) ? rules.map(r => { @@ -52,7 +46,6 @@ function normalizeRules(rules) { if (r.moveTo) actions.push({ type: 'move', folder: r.moveTo }); if (r.copyTarget || r.copyTo) actions.push({ type: 'copy', copyTarget: r.copyTarget || r.copyTo }); const rule = { criterion: r.criterion, actions }; - if (r.decisionThreshold !== undefined) rule.decisionThreshold = r.decisionThreshold; if (r.stopProcessing) rule.stopProcessing = true; if (r.unreadOnly) rule.unreadOnly = true; if (typeof r.minAgeDays === 'number') rule.minAgeDays = r.minAgeDays; @@ -112,42 +105,11 @@ function showTransientIcon(factory, delay = 1500) { async function clearError() { errorPending = false; - clearTimeout(errorTimer); + await storage.local.set({ errorPending: false }); await browser.notifications.clear(ERROR_NOTIFICATION_ID); updateActionIcon(); } -function recordError(context, err) { - let message = 'Unknown error'; - let detail = ''; - if (err instanceof Error) { - message = err.message; - detail = err.stack || ''; - } else if (err && typeof err === 'object') { - message = typeof err.message === 'string' ? err.message : String(err || 'Unknown error'); - detail = typeof err.detail === 'string' ? err.detail : ''; - } else { - message = String(err || 'Unknown error'); - } - errorLog.unshift({ - time: Date.now(), - context, - message, - detail - }); - if (errorLog.length > MAX_ERROR_LOG) { - errorLog.length = MAX_ERROR_LOG; - } - errorPending = true; - updateActionIcon(); - clearTimeout(errorTimer); - errorTimer = setTimeout(() => { - errorPending = false; - updateActionIcon(); - }, ERROR_ICON_TIMEOUT); - browser.runtime.sendMessage({ type: 'sortana:errorLogUpdated', count: errorLog.length }).catch(() => {}); -} - function refreshMenuIcons() { browser.menus.update('apply-ai-rules-list', { icons: iconPaths('eye') }); browser.menus.update('apply-ai-rules-display', { icons: iconPaths('eye') }); @@ -163,16 +125,12 @@ function byteSize(str) { } function replaceInlineBase64(text) { - return text.replace(/(?:data:[^;]+;base64,)?[A-Za-z0-9+/=\r\n]{100,}/g, - m => tokenReduction ? '__BASE64__' : `[base64: ${byteSize(m)} bytes]`); + return text.replace(/[A-Za-z0-9+/]{100,}={0,2}/g, + m => `[base64: ${byteSize(m)} bytes]`); } function sanitizeString(text) { let t = String(text); - if (tokenReduction) { - t = t.replace(//gs, '') - .replace(/url\([^\)]*\)/gi, 'url(__IMG__)'); - } if (stripUrlParams) { t = t.replace(/https?:\/\/[^\s)]+/g, m => { const idx = m.indexOf('?'); @@ -180,7 +138,7 @@ function sanitizeString(text) { }); } if (collapseWhitespace) { - t = t.replace(/[\u200B-\u200D\u2060\s]{2,}/g, ' ').replace(/\n{3,}/g, '\n\n'); + t = t.replace(/[ \t\u00A0]{2,}/g, ' ').replace(/\n{3,}/g, '\n\n'); } return t; } @@ -199,26 +157,12 @@ function collectText(part, bodyParts, attachments) { attachments.push(`${name} (${ct}, ${part.size || byteSize(body)} bytes)`); } else if (ct.startsWith("text/html")) { const doc = new DOMParser().parseFromString(body, 'text/html'); - if (tokenReduction) { - doc.querySelectorAll('script,style').forEach(el => el.remove()); - const walker = doc.createTreeWalker(doc, NodeFilter.SHOW_COMMENT); - let node; - while ((node = walker.nextNode())) { - node.parentNode.removeChild(node); - } - doc.querySelectorAll('*').forEach(el => { - for (const attr of Array.from(el.attributes)) { - if (!['href','src','alt'].includes(attr.name)) { - el.removeAttribute(attr.name); - } - } + if (altTextImages) { + doc.querySelectorAll('img').forEach(img => { + const alt = img.getAttribute('alt') || ''; + img.replaceWith(doc.createTextNode(alt)); }); } - doc.querySelectorAll('img').forEach(img => { - const alt = img.getAttribute('alt') || ''; - const text = altTextImages ? alt : '__IMG__'; - img.replaceWith(doc.createTextNode(text)); - }); if (stripUrlParams) { doc.querySelectorAll('[href]').forEach(a => { const href = a.getAttribute('href'); @@ -245,46 +189,17 @@ function collectText(part, bodyParts, attachments) { } } -function collectRawText(part, bodyParts, attachments) { - if (part.parts && part.parts.length) { - for (const p of part.parts) collectRawText(p, bodyParts, attachments); - return; - } - const ct = (part.contentType || "text/plain").toLowerCase(); - const cd = (part.headers?.["content-disposition"]?.[0] || "").toLowerCase(); - const body = String(part.body || ""); - if (cd.includes("attachment") || !ct.startsWith("text/")) { - const nameMatch = /filename\s*=\s*"?([^";]+)/i.exec(cd) || /name\s*=\s*"?([^";]+)/i.exec(part.headers?.["content-type"]?.[0] || ""); - const name = nameMatch ? nameMatch[1] : ""; - attachments.push(`${name} (${ct}, ${part.size || byteSize(body)} bytes)`); - } else if (ct.startsWith("text/html")) { - const doc = new DOMParser().parseFromString(body, 'text/html'); - bodyParts.push(doc.body.textContent || ""); - } else { - bodyParts.push(body); - } -} - -function buildEmailText(full, applyTransforms = true) { +function buildEmailText(full) { const bodyParts = []; const attachments = []; - const collect = applyTransforms ? collectText : collectRawText; - collect(full, bodyParts, attachments); + collectText(full, bodyParts, attachments); const headers = Object.entries(full.headers || {}) .map(([k, v]) => `${k}: ${v.join(' ')}`) .join('\n'); const attachInfo = `Attachments: ${attachments.length}` + (attachments.length ? "\n" + attachments.map(a => ` - ${a}`).join('\n') : ""); - let combined = `${headers}\n${attachInfo}\n\n${bodyParts.join('\n')}`.trim(); - if (applyTransforms && tokenReduction) { - const seen = new Set(); - combined = combined.split('\n').filter(l => { - if (seen.has(l)) return false; - seen.add(l); - return true; - }).join('\n'); - } - return applyTransforms ? sanitizeString(combined) : combined; + const combined = `${headers}\n${attachInfo}\n\n${bodyParts.join('\n')}`.trim(); + return sanitizeString(combined); } function updateTimingStats(elapsed) { @@ -318,19 +233,7 @@ async function processMessage(id) { updateActionIcon(); try { const full = await messenger.messages.getFull(id); - const snapshot = AiClassifier.getConfig(); - const rules = structuredClone(aiRules); - const originalText = buildEmailText(full, false); - let text = buildEmailText(full); - if (tokenReduction) { - const limit = snapshot.inputCharacterLimit; - if (text.length > limit) { - text = text.slice(0, limit); - } - } - if (showDebugTab) { - await storage.local.set({ lastFullText: originalText, lastPromptText: text }); - } + const text = buildEmailText(full); let hdr; let currentTags = []; let alreadyRead = false; @@ -347,8 +250,7 @@ async function processMessage(id) { identityId = null; } - const candidates = []; - for (const [index, rule] of rules.entries()) { + for (const rule of aiRules) { if (rule.enabled === false) { continue; } @@ -375,10 +277,8 @@ async function processMessage(id) { } } } - const cacheKey = await AiClassifier.buildCacheKey(id, rule.criterion, snapshot); - candidates.push({ id: `rule_${index}`, rule, cacheKey }); - } - for await (const { rule, result: { matched } } of AiClassifier.classifyRules(text, candidates, snapshot)) { + const cacheKey = await AiClassifier.buildCacheKey(id, rule.criterion); + const matched = await AiClassifier.classifyText(text, rule.criterion, cacheKey); if (matched) { for (const act of (rule.actions || [])) { if (act.type === 'tag' && act.tagKey) { @@ -422,14 +322,16 @@ async function processMessage(id) { const elapsed = Date.now() - currentStart; currentStart = 0; updateTimingStats(elapsed); - await storage.local.set({ classifyStats: timingStats }); + await storage.local.set({ classifyStats: timingStats, errorPending: true }); + errorPending = true; logger.aiLog("failed to apply AI rules", { level: 'error' }, e); - recordError("Failed to apply AI rules", e); + setIcon(ICONS.error()); browser.notifications.create(ERROR_NOTIFICATION_ID, { type: 'basic', iconUrl: browser.runtime.getURL('resources/img/logo.png'), title: 'Sortana Error', - message: 'Failed to apply AI rules' + message: 'Failed to apply AI rules', + buttons: [{ title: 'Dismiss' }] }); } } @@ -461,8 +363,18 @@ async function clearCacheForMessages(idsInput) { aiRules = normalizeRules(stored); } - for (const msg of ids) await AiClassifier.clearCacheForMessage(msg?.id ?? msg); - showTransientIcon(ICONS.circle); + const keys = []; + for (const msg of ids) { + const id = msg?.id ?? msg; + for (const rule of aiRules) { + const key = await AiClassifier.buildCacheKey(id, rule.criterion); + keys.push(key); + } + } + if (keys.length) { + await AiClassifier.removeCacheEntries(keys); + showTransientIcon(ICONS.circle); + } } (async () => { @@ -479,13 +391,8 @@ async function clearCacheForMessages(idsInput) { } try { - const store = await storage.local.get(["systemOneProcessAll", "systemOneBatchSize", "apiType", "decisionThreshold", "inputCharacterLimit", "endpoint", "model", "apiKey", "openaiOrganization", "openaiProject", "customSystemPrompt", "aiParams", "debugLogging", "htmlToMarkdown", "stripUrlParams", "altTextImages", "collapseWhitespace", "tokenReduction", "aiRules", "theme", "showDebugTab"]); + const store = await storage.local.get(["endpoint", "templateName", "customTemplate", "customSystemPrompt", "aiParams", "debugLogging", "htmlToMarkdown", "stripUrlParams", "altTextImages", "collapseWhitespace", "aiRules", "theme", "errorPending"]); logger.setDebug(store.debugLogging); - const { migratedInputLimit } = await import(browser.runtime.getURL('modules/classificationConfig.js')); - if (store.inputCharacterLimit === undefined) { - store.inputCharacterLimit = migratedInputLimit(store); - await storage.local.set({ inputCharacterLimit: store.inputCharacterLimit }); - } await AiClassifier.setConfig(store); userTheme = store.theme || 'auto'; currentTheme = userTheme === 'auto' ? await detectSystemTheme() : userTheme; @@ -494,8 +401,7 @@ async function clearCacheForMessages(idsInput) { stripUrlParams = store.stripUrlParams === true; altTextImages = store.altTextImages === true; collapseWhitespace = store.collapseWhitespace === true; - tokenReduction = store.tokenReduction === true; - showDebugTab = store.showDebugTab === true; + errorPending = store.errorPending === true; const savedStats = await storage.local.get('classifyStats'); if (savedStats.classifyStats && typeof savedStats.classifyStats === 'object') { Object.assign(timingStats, savedStats.classifyStats); @@ -511,9 +417,6 @@ async function clearCacheForMessages(idsInput) { aiRules = normalizeRules(newRules); logger.aiLog("aiRules updated from storage change", { debug: true }, aiRules); } - const configChanges = Object.fromEntries(Object.entries(changes).map(([key, change]) => [key, change.newValue])); - AiClassifier.setConfig(configChanges); - if (changes.aiCache) AiClassifier.replaceCache(changes.aiCache.newValue); if (changes.htmlToMarkdown) { htmlToMarkdown = changes.htmlToMarkdown.newValue === true; logger.aiLog("htmlToMarkdown updated from storage change", { debug: true }, htmlToMarkdown); @@ -530,12 +433,9 @@ async function clearCacheForMessages(idsInput) { collapseWhitespace = changes.collapseWhitespace.newValue === true; logger.aiLog("collapseWhitespace updated from storage change", { debug: true }, collapseWhitespace); } - if (changes.tokenReduction) { - tokenReduction = changes.tokenReduction.newValue === true; - logger.aiLog("tokenReduction updated from storage change", { debug: true }, tokenReduction); - } - if (changes.showDebugTab) { - showDebugTab = changes.showDebugTab.newValue === true; + if (changes.errorPending) { + errorPending = changes.errorPending.newValue === true; + updateActionIcon(); } if (changes.theme) { userTheme = changes.theme.newValue || 'auto'; @@ -645,10 +545,10 @@ async function clearCacheForMessages(idsInput) { logger.aiLog("sortana:test – criterion", { debug: true }, criterion); try { - logger.aiLog("Calling AiClassifier.classify()", { debug: true }); - const result = await AiClassifier.classify(text, criterion, { threshold: msg.decisionThreshold ?? AiClassifier.getConfig().decisionThreshold }); + logger.aiLog("Calling AiClassifier.classifyText()", { debug: true }); + const result = await AiClassifier.classifyText(text, criterion); logger.aiLog("classify() returned", { debug: true }, result); - return { ...result, match: result.matched }; + return { match: result }; } catch (err) { logger.aiLog("Error in classify()", { level: 'error' }, err); @@ -695,11 +595,13 @@ async function clearCacheForMessages(idsInput) { aiRules = normalizeRules(stored); } const results = []; - const snapshot = AiClassifier.getConfig(); - for (const rule of structuredClone(aiRules)) { - const key = await AiClassifier.buildCacheKey(id, rule.criterion, snapshot); - const detail = AiClassifier.getCachedDetails(key, rule.decisionThreshold ?? snapshot.decisionThreshold); - if (detail) results.push({ criterion: rule.criterion, ...detail }); + for (const rule of aiRules) { + const key = await AiClassifier.buildCacheKey(id, rule.criterion); + const matched = AiClassifier.getCachedResult(key); + const reason = AiClassifier.getReason(key); + if (matched !== null || reason) { + results.push({ criterion: rule.criterion, matched, reason }); + } } return { subject, results }; } catch (e) { @@ -725,24 +627,8 @@ async function clearCacheForMessages(idsInput) { logger.aiLog("failed to clear cache for message", { level: 'error' }, e); return { ok: false }; } - } else if (msg?.type === "sortana:resetTimingStats") { - const last = timingStats.last; - timingStats.count = 0; - timingStats.mean = 0; - timingStats.m2 = 0; - timingStats.total = 0; - timingStats.last = typeof last === 'number' ? last : -1; - await storage.local.set({ classifyStats: timingStats }); - return { ok: true }; - } else if (msg?.type === "sortana:getCacheSize") { - return { count: await AiClassifier.getCacheSize() }; } else if (msg?.type === "sortana:getQueueCount") { return { count: queuedCount + (processing ? 1 : 0) }; - } else if (msg?.type === "sortana:getErrorLog") { - return { errors: errorLog.slice() }; - } else if (msg?.type === "sortana:recordError") { - recordError(msg.context || "Sortana Error", { message: msg.message, detail: msg.detail }); - return { ok: true }; } else if (msg?.type === "sortana:getTiming") { const t = timingStats; const std = t.count > 1 ? Math.sqrt(t.m2 / (t.count - 1)) : 0; @@ -774,7 +660,6 @@ async function clearCacheForMessages(idsInput) { // Catch any unhandled rejections window.addEventListener("unhandledrejection", ev => { logger.aiLog("Unhandled promise rejection", { level: 'error' }, ev.reason); - recordError("Unhandled promise rejection", ev.reason); }); browser.notifications.onClicked.addListener(id => { diff --git a/build-xpi.sh b/build-xpi.sh deleted file mode 100755 index 20c6e15..0000000 --- a/build-xpi.sh +++ /dev/null @@ -1,77 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -release_dir="$script_dir/release" -manifest="$script_dir/manifest.json" - -if [[ ! -f "$manifest" ]]; then - echo "manifest.json not found at $manifest" >&2 - exit 1 -fi - -if ! command -v zip >/dev/null 2>&1; then - echo "zip is required to build the XPI." >&2 - exit 1 -fi - -if command -v jq >/dev/null 2>&1; then - version="$(jq -r '.version // empty' "$manifest")" -else - if ! command -v python3 >/dev/null 2>&1; then - echo "python3 is required to read manifest.json without jq." >&2 - exit 1 - fi - version="$(python3 - <<'PY' -import json -import sys -with open(sys.argv[1], 'r', encoding='utf-8') as f: - data = json.load(f) -print(data.get('version', '') or '') -PY -"$manifest")" -fi - -if [[ -z "$version" ]]; then - echo "No version found in manifest.json" >&2 - exit 1 -fi - -mkdir -p "$release_dir" - -xpi_name="sortana-$version.xpi" -zip_path="$release_dir/ai-filter-$version.zip" -xpi_path="$release_dir/$xpi_name" - -rm -f "$zip_path" "$xpi_path" - -mapfile -d '' files < <( - find "$script_dir" -type f \ - ! -name '*.sln' \ - ! -name '*.ps1' \ - ! -name '*.sh' \ - ! -path "$release_dir/*" \ - ! -path "$script_dir/.vs/*" \ - ! -path "$script_dir/.git/*" \ - -printf '%P\0' -) - -if [[ ${#files[@]} -eq 0 ]]; then - echo "No files found to package." >&2 - exit 0 -fi - -for rel in "${files[@]}"; do - full="$script_dir/$rel" - size=$(stat -c '%s' "$full") - echo "Zipping: $rel <- $full ($size bytes)" -done - -( - cd "$script_dir" - printf '%s\n' "${files[@]}" | zip -q -9 -@ "$zip_path" -) - -mv -f "$zip_path" "$xpi_path" - -echo "Built XPI at: $xpi_path" diff --git a/details.html b/details.html index e84bf2e..d15a3c9 100644 --- a/details.html +++ b/details.html @@ -4,33 +4,6 @@ AI Details -
diff --git a/details.js b/details.js index a4534d3..f306e01 100644 --- a/details.js +++ b/details.js @@ -51,39 +51,15 @@ async function loadMessage(id) { article.className = `message ${color} mb-4`; const header = document.createElement('div'); header.className = 'message-header'; - const criterion = document.createElement('p'); - criterion.textContent = r.criterion; - header.appendChild(criterion); + header.innerHTML = `

${r.criterion}

`; const body = document.createElement('div'); body.className = 'message-body'; const status = document.createElement('p'); status.textContent = r.matched ? 'Matched' : 'Did not match'; - if (r.backend === 'systemone') { - status.textContent += ' under current threshold'; - status.classList.add('mb-2'); - body.appendChild(status); - const percentage = r.probability * 100; - const bar = document.createElement('div'); - bar.className = `probability-bar ${color}`; - bar.setAttribute('role', 'progressbar'); - bar.setAttribute('aria-label', 'Match probability'); - bar.setAttribute('aria-valuemin', '0'); - bar.setAttribute('aria-valuemax', '100'); - bar.setAttribute('aria-valuenow', String(percentage)); - bar.title = `Threshold: ${r.threshold * 100}%${r.model ? ` · Model: ${r.model}` : ''}`; - const fill = document.createElement('div'); - fill.className = 'probability-fill'; - fill.style.width = `${percentage}%`; - const value = document.createElement('span'); - value.className = 'probability-value'; - value.textContent = `${percentage.toFixed(2)}%`; - bar.append(fill, value); - body.appendChild(bar); - } else { - const pre = document.createElement('pre'); - pre.textContent = r.reason || ''; - body.append(status, pre); - } + const pre = document.createElement('pre'); + pre.textContent = r.reason || ''; + body.appendChild(status); + body.appendChild(pre); article.appendChild(header); article.appendChild(body); container.appendChild(article); diff --git a/manifest.json b/manifest.json index b304bc0..c3b45a7 100644 --- a/manifest.json +++ b/manifest.json @@ -1,12 +1,13 @@ { "manifest_version": 2, "name": "Sortana", - "version": "4.1.0", + "version": "2.1.1", "default_locale": "en-US", "applications": { "gecko": { "id": "ai-filter@jordanwages", - "strict_min_version": "128.0" + "strict_min_version": "128.0", + "strict_max_version": "139.*" } }, "icons": { diff --git a/modules/AiClassifier.js b/modules/AiClassifier.js index 603816f..b35cb2c 100644 --- a/modules/AiClassifier.js +++ b/modules/AiClassifier.js @@ -1,209 +1,342 @@ "use strict"; -import { aiLog, setDebug } from '../logger.js'; -import { CONFIG_DEFAULTS, validateSettings, validateThreshold } from './classificationConfig.js'; -import * as chat from './backends/chatCompletions.js'; -import * as systemone from './backends/systemOne.js'; +import { aiLog, setDebug } from "../logger.js"; +import { DEFAULT_AI_PARAMS } from "./defaultParams.js"; + const storage = (globalThis.messenger ?? globalThis.browser).storage; -const adapters = { 'chat-completions': chat, systemone }; -let config = structuredClone(CONFIG_DEFAULTS); -let cache = new Map(); -let loaded = false; -let loading; -let generation = 0; -export function normalizeEndpointBase(endpoint) { - if (typeof endpoint !== 'string' || !endpoint.trim()) return ''; - return endpoint.trim().replace(/\/+$/, '').replace(/\/v1(?:\/(?:chat\/completions|completions|models|systemone))?$/i, ''); -} -function urlFor(endpoint, path) { - const base = normalizeEndpointBase(endpoint); - return base ? `${/^https?:\/\//i.test(base) ? base : `https://${base}`}${path}` : ''; -} -export function buildEndpointUrl(endpoint, apiType = 'chat-completions') { - if (!adapters[apiType]) throw new Error('Unknown API type.'); - return urlFor(endpoint, adapters[apiType].path); -} -export function buildModelsUrl(endpoint) { return urlFor(endpoint, '/v1/models'); } -export function getConfig() { return structuredClone(config); } -export function setConfig(update = {}) { - validateSettings(update); - for (const key of Object.keys(CONFIG_DEFAULTS)) { - if (update[key] !== undefined) config[key] = structuredClone(update[key]); +let Services; +try { + if (typeof globalThis !== "undefined" && globalThis.Services) { + Services = globalThis.Services; + } else if (typeof ChromeUtils !== "undefined" && ChromeUtils.importESModule) { + ({ Services } = ChromeUtils.importESModule("resource://gre/modules/Services.sys.mjs")); } - config.aiParams = { ...CONFIG_DEFAULTS.aiParams, ...config.aiParams }; - for (const key of ['model', 'apiKey', 'openaiOrganization', 'openaiProject']) config[key] = String(config[key]).trim(); - setDebug(config.debugLogging); +} catch (e) { + Services = undefined; } -async function hash(value) { - const digest = await crypto.subtle.digest('SHA-256', new TextEncoder().encode(value)); - return Array.from(new Uint8Array(digest), b => b.toString(16).padStart(2, '0')).join(''); -} -async function messageHash(id) { - const api = globalThis.messenger ?? globalThis.browser; - if (typeof id === 'number' && api.messages?.get) { - const header = await api.messages.get(id); - id = header.headerMessageId || id; + +const SYSTEM_PREFIX = `You are an email-classification assistant. +Read the email below and the classification criterion provided by the user. +`; + +const DEFAULT_CUSTOM_SYSTEM_PROMPT = "Determine whether the email satisfies the user's criterion."; + +const SYSTEM_SUFFIX = ` +Return ONLY a JSON object on a single line of the form: +{"match": true} - if the email satisfies the criterion +{"match": false} - otherwise + +Do not add any other keys, text, or formatting.`; + +let gEndpoint = "http://127.0.0.1:5000/v1/classify"; +let gTemplateName = "openai"; +let gCustomTemplate = ""; +let gCustomSystemPrompt = DEFAULT_CUSTOM_SYSTEM_PROMPT; +let gTemplateText = ""; + +let gAiParams = Object.assign({}, DEFAULT_AI_PARAMS); + +let gCache = new Map(); +let gCacheLoaded = false; + +function sha256HexSync(str) { + try { + const hasher = Cc["@mozilla.org/security/hash;1"].createInstance(Ci.nsICryptoHash); + hasher.init(Ci.nsICryptoHash.SHA256); + const data = new TextEncoder().encode(str); + hasher.update(data, data.length); + const binary = hasher.finish(false); + return Array.from(binary, c => ("0" + c.charCodeAt(0).toString(16)).slice(-2)).join(""); + } catch (e) { + aiLog(`sha256HexSync failed`, { level: 'error' }, e); + return ""; } - return hash(String(id)); } -function stable(value) { - if (Array.isArray(value)) return value.map(stable); - if (value && typeof value === 'object') return Object.fromEntries(Object.keys(value).sort().map(k => [k, stable(value[k])])); - return value; -} -export async function buildCacheKey(id, criterion, snapshot = getConfig()) { - const fingerprint = { - backend: snapshot.apiType, endpoint: buildEndpointUrl(snapshot.endpoint, snapshot.apiType), - request: adapters[snapshot.apiType].buildRequest('', criterion, snapshot), - organization: snapshot.apiType === 'chat-completions' ? snapshot.openaiOrganization : '', - project: snapshot.apiType === 'chat-completions' ? snapshot.openaiProject : '', - preprocessing: Object.fromEntries(['htmlToMarkdown', 'stripUrlParams', 'altTextImages', 'collapseWhitespace', 'tokenReduction', 'inputCharacterLimit'].map(k => [k, snapshot[k]])) - }; - return `v2:${await messageHash(id)}:${await hash(JSON.stringify(stable(fingerprint)))}`; -} -export function validCacheEntry(key, entry) { - return /^v2:[a-f0-9]{64}:[a-f0-9]{64}$/.test(key) && entry?.version === 2 && - entry.messageHash === key.split(':')[1] && typeof entry.model === 'string' && - (entry.backend === 'systemone' - ? typeof entry.probability === 'number' && Number.isFinite(entry.probability) && entry.probability >= 0 && entry.probability <= 1 && entry.reason === null - : entry.backend === 'chat-completions' && typeof entry.matched === 'boolean' && entry.probability === null && (entry.reason === null || typeof entry.reason === 'string')); -} -export function replaceCache(data = {}) { - cache = new Map(Object.entries(data || {}).filter(([key, entry]) => validCacheEntry(key, entry))); - loaded = true; - generation++; -} -async function saveCache() { await storage.local.set({ aiCache: Object.fromEntries(cache) }); } -export async function init() { - if (loaded) return; - if (!loading) loading = (async () => { - const { aiCache = {}, aiReasonCache } = await storage.local.get(['aiCache', 'aiReasonCache']); - replaceCache(aiCache); - if (Object.keys(aiCache || {}).length !== cache.size) await saveCache(); - if (aiReasonCache !== undefined) await storage.local.remove('aiReasonCache'); - })().finally(() => { loading = null; }); - await loading; -} -function withPolicy(entry, threshold) { - const isDecision = entry.backend === 'systemone'; - if (isDecision) validateThreshold(threshold); - return { matched: isDecision ? entry.probability >= threshold : entry.matched, - reason: entry.reason, probability: entry.probability, threshold: isDecision ? threshold : null, - backend: entry.backend, model: entry.model }; -} -export function getCachedDetails(key, threshold = config.decisionThreshold) { - const entry = cache.get(key); - return entry ? withPolicy(entry, threshold) : null; -} -export function getCachedResult(key, threshold) { return getCachedDetails(key, threshold)?.matched ?? null; } -export function getReason(key) { return cache.get(key)?.reason ?? null; } -async function sendRequest(payload, snapshot) { - try { await storage.local.set({ lastPayload: payload }); } - catch (error) { aiLog('Failed to save last payload', { level: 'warn' }, error); } - const headers = { 'Content-Type': 'application/json' }; - if (snapshot.apiKey) headers.Authorization = `Bearer ${snapshot.apiKey}`; - if (snapshot.apiType === 'chat-completions') { - if (snapshot.openaiOrganization) headers['OpenAI-Organization'] = snapshot.openaiOrganization; - if (snapshot.openaiProject) headers['OpenAI-Project'] = snapshot.openaiProject; + +async function sha256Hex(str) { + if (typeof crypto?.subtle?.digest === "function") { + const buf = await crypto.subtle.digest("SHA-256", new TextEncoder().encode(str)); + return Array.from(new Uint8Array(buf), b => b.toString(16).padStart(2, "0")).join(""); } - const endpoint = buildEndpointUrl(snapshot.endpoint, snapshot.apiType); - const response = await fetch(endpoint, { method: 'POST', headers, body: JSON.stringify(payload) }); - if (!response.ok) { - let detail = ''; + return sha256HexSync(str); +} + +async function resolveHeaderId(id) { + if (typeof id === "number" && typeof messenger?.messages?.get === "function") { try { - const body = await response.json(); - const message = body?.error?.message; - if (typeof message === 'string') detail = ` Server response: ${message.slice(0, 300)}.`; - } catch { /* Non-JSON error responses still report the URL and status. */ } - const hint = response.status === 404 && snapshot.apiType === 'systemone' - ? ' Verify that the running server build supports /v1/systemone and the selected decision model.' : ''; - throw new Error(`Classification request failed: HTTP ${response.status} at ${endpoint}.${detail}${hint}`); + const hdr = await messenger.messages.get(id); + if (hdr?.headerMessageId) { + return hdr.headerMessageId; + } + } catch (e) { + aiLog(`Failed to resolve headerMessageId for ${id}`, { level: 'warn' }, e); + } } - return response.json(); + return String(id); } -export async function classify(text, criterion, { cacheKey = null, snapshot = getConfig(), threshold = snapshot.decisionThreshold } = {}) { - await init(); - if (snapshot.apiType === 'systemone') validateThreshold(threshold); - const cached = getCachedDetails(cacheKey, threshold); - if (cached) return cached; - const epoch = generation; - const adapter = adapters[snapshot.apiType]; - const payload = adapter.buildRequest(text, criterion, snapshot); - const raw = await sendRequest(payload, snapshot); - const entry = { ...adapter.parseResponse(raw), backend: snapshot.apiType, - model: typeof raw.model === 'string' ? raw.model : snapshot.model, version: 2, - messageHash: cacheKey?.split(':')[1] }; - if (cacheKey && epoch === generation) { - cache.set(cacheKey, entry); - await saveCache(); +async function buildCacheKey(id, criterion) { + const resolvedId = await resolveHeaderId(id); + if (Services) { + return sha256HexSync(`${resolvedId}|${criterion}`); } - return withPolicy(entry, threshold); + return sha256Hex(`${resolvedId}|${criterion}`); } -// Yield lazily so the action runner can stop without starting the next request. -// Candidates have precomputed keys, allowing actions to move/delete the message. -export async function* classifyRules(text, candidates, snapshot = getConfig()) { - await init(); - validateSettings(snapshot); - if (snapshot.apiType !== 'systemone') { - for (const candidate of candidates) { - const result = await classify(text, candidate.rule.criterion, { - cacheKey: candidate.cacheKey, snapshot, - threshold: candidate.rule.decisionThreshold ?? snapshot.decisionThreshold - }); - yield { rule: candidate.rule, result }; - } + +async function loadCache() { + if (gCacheLoaded) { return; } - const limit = snapshot.systemOneProcessAll ? Infinity : snapshot.systemOneBatchSize; - // Keep received evidence locally even if persistence is cleared during this run. - const evidence = new Map(); - for (const candidate of candidates) { - validateThreshold(candidate.rule.decisionThreshold ?? snapshot.decisionThreshold); - const entry = cache.get(candidate.cacheKey); - if (entry) evidence.set(candidate.cacheKey, entry); - } - for (let index = 0; index < candidates.length; index++) { - const candidate = candidates[index]; - if (!evidence.has(candidate.cacheKey)) { - const pending = new Map(); - for (let next = index; next < candidates.length && pending.size < limit; next++) { - const item = candidates[next]; - if (!evidence.has(item.cacheKey) && !pending.has(item.cacheKey)) { - pending.set(item.cacheKey, { ...item, criterion: item.rule.criterion }); + aiLog(`[AiClassifier] Loading cache`, {debug: true}); + try { + const { aiCache, aiReasonCache } = await storage.local.get(["aiCache", "aiReasonCache"]); + if (aiCache) { + for (let [k, v] of Object.entries(aiCache)) { + if (v && typeof v === "object") { + gCache.set(k, { matched: v.matched ?? null, reason: v.reason || "" }); + } else { + gCache.set(k, { matched: v, reason: "" }); } } - const questions = [...pending.values()]; - const epoch = generation; - const raw = await sendRequest(systemone.buildBatchRequest(text, questions, snapshot), snapshot); - // Parse the complete batch before accepting any of its evidence. - const parsed = systemone.parseBatchResponse(raw, questions); - const entries = questions.map((question, i) => [question.cacheKey, { - ...parsed[i], backend: snapshot.apiType, version: 2, - model: typeof raw.model === 'string' ? raw.model : snapshot.model, - messageHash: question.cacheKey.split(':')[1] - }]); - for (const [key, entry] of entries) evidence.set(key, entry); - if (epoch === generation) { - for (const [key, entry] of entries) cache.set(key, entry); - await saveCache(); - } + aiLog(`[AiClassifier] Loaded ${gCache.size} cache entries`, {debug: true}); + } else { + aiLog(`[AiClassifier] Cache is empty`, {debug: true}); } - yield { rule: candidate.rule, result: withPolicy(evidence.get(candidate.cacheKey), - candidate.rule.decisionThreshold ?? snapshot.decisionThreshold) }; + if (aiReasonCache) { + aiLog(`[AiClassifier] Migrating ${Object.keys(aiReasonCache).length} reason entries`, {debug: true}); + for (let [k, reason] of Object.entries(aiReasonCache)) { + let entry = gCache.get(k) || { matched: null, reason: "" }; + entry.reason = reason; + gCache.set(k, entry); + } + await storage.local.remove("aiReasonCache"); + await storage.local.set({ aiCache: Object.fromEntries(gCache) }); + } + } catch (e) { + aiLog(`Failed to load cache`, {level: 'error'}, e); + } + gCacheLoaded = true; +} + + +async function saveCache(updatedKey, updatedValue) { + if (typeof updatedKey !== "undefined") { + aiLog(`[AiClassifier] ⮡ Persisting entry '${updatedKey}' → ${updatedValue}`, {debug: true}); + } + try { + await storage.local.set({ aiCache: Object.fromEntries(gCache) }); + } catch (e) { + aiLog(`Failed to save cache`, {level: 'error'}, e); } } -export async function classifyText(text, criterion, cacheKey = null) { return (await classify(text, criterion, { cacheKey })).matched; } -export async function removeCacheEntries(keys = []) { - await init(); generation++; - for (const key of Array.isArray(keys) ? keys : [keys]) cache.delete(key); - await saveCache(); + +async function loadTemplate(name) { + try { + const url = typeof browser !== "undefined" && browser.runtime?.getURL + ? browser.runtime.getURL(`prompt_templates/${name}.txt`) + : `resource://aifilter/prompt_templates/${name}.txt`; + const res = await fetch(url); + if (res.ok) { + return await res.text(); + } + } catch (e) { + aiLog(`Failed to load template '${name}':`, {level: 'error'}, e); + } + return ""; } -export async function clearCacheForMessage(id) { - await init(); - const identifier = await messageHash(id); - await removeCacheEntries([...cache].filter(([, entry]) => entry.messageHash === identifier).map(([key]) => key)); + +function loadTemplateSync(name) { + if (!Services?.tm?.spinEventLoopUntil) { + throw new Error("loadTemplateSync requires Services"); + } + let text = ""; + let done = false; + loadTemplate(name).then(t => { text = t; }).catch(() => {}).finally(() => { done = true; }); + Services.tm.spinEventLoopUntil(() => done); + return text; } -export async function clearCache() { await init(); generation++; cache.clear(); await saveCache(); } -export async function getCacheSize() { await init(); return cache.size; } + +async function setConfig(config = {}) { + if (config.endpoint) { + gEndpoint = config.endpoint; + } + if (config.templateName) { + gTemplateName = config.templateName; + } + if (typeof config.customTemplate === "string") { + gCustomTemplate = config.customTemplate; + } + if (typeof config.customSystemPrompt === "string") { + gCustomSystemPrompt = config.customSystemPrompt; + } + if (config.aiParams && typeof config.aiParams === "object") { + for (let [k, v] of Object.entries(config.aiParams)) { + if (k in gAiParams && typeof v !== "undefined") { + gAiParams[k] = v; + } + } + } + if (typeof config.debugLogging === "boolean") { + setDebug(config.debugLogging); + } + if (gTemplateName === "custom") { + gTemplateText = gCustomTemplate; + } else if (Services?.tm?.spinEventLoopUntil) { + gTemplateText = loadTemplateSync(gTemplateName); + } else { + gTemplateText = await loadTemplate(gTemplateName); + } + aiLog(`[AiClassifier] Endpoint set to ${gEndpoint}`, {debug: true}); + aiLog(`[AiClassifier] Template set to ${gTemplateName}`, {debug: true}); +} + +function buildSystemPrompt() { + return SYSTEM_PREFIX + (gCustomSystemPrompt || DEFAULT_CUSTOM_SYSTEM_PROMPT) + SYSTEM_SUFFIX; +} + +function buildPrompt(body, criterion) { + aiLog(`[AiClassifier] Building prompt with criterion: "${criterion}"`, {debug: true}); + const data = { + system: buildSystemPrompt(), + email: body, + query: criterion, + }; + let template = gTemplateText || loadTemplateSync(gTemplateName); + return template.replace(/{{\s*(\w+)\s*}}/g, (m, key) => data[key] || ""); +} + +function getCachedResult(cacheKey) { + if (!gCacheLoaded) { + return null; + } + if (cacheKey && gCache.has(cacheKey)) { + aiLog(`[AiClassifier] Cache hit for key: ${cacheKey}`, {debug: true}); + const entry = gCache.get(cacheKey); + return entry?.matched ?? null; + } + return null; +} + +function getReason(cacheKey) { + if (!gCacheLoaded) { + return null; + } + const entry = gCache.get(cacheKey); + return cacheKey && entry ? entry.reason || null : null; +} + +function buildPayload(text, criterion) { + let payloadObj = Object.assign({ + prompt: buildPrompt(text, criterion) + }, gAiParams); + return JSON.stringify(payloadObj); +} + +function parseMatch(result) { + const rawText = result.choices?.[0]?.text || ""; + const thinkText = rawText.match(/[\s\S]*?<\/think>/gi)?.join('') || ''; + aiLog('[AiClassifier] ⮡ Reasoning:', {debug: true}, thinkText); + const cleanedText = rawText.replace(/[\s\S]*?<\/think>/gi, "").trim(); + aiLog('[AiClassifier] ⮡ Cleaned Response Text:', {debug: true}, cleanedText); + const obj = JSON.parse(cleanedText); + const matched = obj.matched === true || obj.match === true; + return { matched, reason: thinkText }; +} + +function cacheEntry(cacheKey, matched, reason) { + if (!cacheKey) { + return; + } + aiLog(`[AiClassifier] Caching entry '${cacheKey}'`, {debug: true}); + const entry = gCache.get(cacheKey) || { matched: null, reason: "" }; + if (typeof matched === "boolean") { + entry.matched = matched; + } + if (typeof reason === "string") { + entry.reason = reason; + } + gCache.set(cacheKey, entry); + saveCache(cacheKey, entry); +} + +async function removeCacheEntries(keys = []) { + if (!Array.isArray(keys)) { + keys = [keys]; + } + if (!gCacheLoaded) { + await loadCache(); + } + let removed = false; + for (let key of keys) { + if (gCache.delete(key)) { + removed = true; + aiLog(`[AiClassifier] Removed cache entry '${key}'`, {debug: true}); + } + } + if (removed) { + await saveCache(); + } +} + +async function clearCache() { + if (!gCacheLoaded) { + await loadCache(); + } + if (gCache.size > 0) { + gCache.clear(); + await saveCache(); + aiLog(`[AiClassifier] Cleared cache`, {debug: true}); + } +} + +async function getCacheSize() { + if (!gCacheLoaded) { + await loadCache(); + } + return gCache.size; +} + + +async function classifyText(text, criterion, cacheKey = null) { + if (!gCacheLoaded) { + await loadCache(); + } + const cached = getCachedResult(cacheKey); + if (cached !== null) { + return cached; + } + + const payload = buildPayload(text, criterion); + + aiLog(`[AiClassifier] Sending classification request to ${gEndpoint}`, {debug: true}); + aiLog(`[AiClassifier] Classification request payload:`, { debug: true }, payload); + + try { + const response = await fetch(gEndpoint, { + method: "POST", + headers: { "Content-Type": "application/json" }, + body: payload, + }); + + if (!response.ok) { + aiLog(`HTTP status ${response.status}`, {level: 'warn'}); + return false; + } + + const result = await response.json(); + aiLog(`[AiClassifier] Received response:`, {debug: true}, result); + const parsed = parseMatch(result); + cacheEntry(cacheKey, parsed.matched, parsed.reason); + return parsed.matched; + } catch (e) { + aiLog(`HTTP request failed`, {level: 'error'}, e); + return false; + } +} + +async function init() { + await loadCache(); +} + +export { classifyText, setConfig, removeCacheEntries, clearCache, getReason, getCachedResult, buildCacheKey, getCacheSize, init }; diff --git a/modules/backends/chatCompletions.js b/modules/backends/chatCompletions.js deleted file mode 100644 index 38d9771..0000000 --- a/modules/backends/chatCompletions.js +++ /dev/null @@ -1,81 +0,0 @@ -const SYSTEM_PREFIX = `You are an email-classification assistant. -Read the email below and the classification criterion provided by the user. -`; - -const DEFAULT_CUSTOM_SYSTEM_PROMPT = "Determine whether the email satisfies the user's criterion."; - -const SYSTEM_SUFFIX = ` -Return ONLY a JSON object on a single line of the form: -{"match": true, "reason": ""} - if the email satisfies the criterion -{"match": false, "reason": ""} - otherwise - -Do not add any other keys, text, or formatting.`; - -function extractLastJsonObject(text) { - let last = null; - let start = -1; - let depth = 0; - let inString = false; - let escape = false; - - for (let i = 0; i < text.length; i += 1) { - const ch = text[i]; - if (inString) { - if (escape) { - escape = false; - continue; - } - if (ch === "\\") { - escape = true; - continue; - } - if (ch === "\"") { - inString = false; - } - continue; - } - if (ch === "\"") { - inString = true; - continue; - } - if (ch === "{") { - if (depth === 0) { - start = i; - } - depth += 1; - continue; - } - if (ch === "}" && depth > 0) { - depth -= 1; - if (depth === 0 && start !== -1) { - last = text.slice(start, i + 1); - start = -1; - } - } - } - - return last; -} - -export const path = '/v1/chat/completions'; -export function buildRequest(text, criterion, config) { - const payload = { - messages: [ - { role: 'system', content: SYSTEM_PREFIX + (config.customSystemPrompt || DEFAULT_CUSTOM_SYSTEM_PROMPT) + SYSTEM_SUFFIX }, - { role: 'user', content: `**Email Contents**\n\`\`\`\n${text}\n\`\`\`\nClassification Criterion: ${criterion}` } - ], ...config.aiParams - }; - if (config.model) payload.model = config.model; - return payload; -} -export function parseResponse(result) { - const content = result?.choices?.[0]?.message?.content; - if (typeof content !== 'string') throw new Error('Chat response missing text content.'); - const candidate = extractLastJsonObject(content); - if (!candidate) throw new Error('No JSON object found in AI response.'); - const obj = JSON.parse(candidate); - const matched = Object.hasOwn(obj, 'match') ? obj.match : obj.matched; - if (typeof matched !== 'boolean') throw new Error('AI response missing valid match boolean.'); - const reason = obj.reason ?? obj.reasoning ?? obj.explaination; - return { matched, reason: typeof reason === 'string' ? reason : null, probability: null }; -} diff --git a/modules/backends/systemOne.js b/modules/backends/systemOne.js deleted file mode 100644 index 70627f1..0000000 --- a/modules/backends/systemOne.js +++ /dev/null @@ -1,22 +0,0 @@ -export const path = '/v1/systemone'; -export function buildRequest(text, criterion, config) { - return buildBatchRequest(text, [{ id: 'match', criterion }], config); -} -export function buildBatchRequest(text, questions, config) { - const payload = { state: text, questions: Object.fromEntries(questions.map(({ id, criterion }) => - [id, { type: 'noul', instructions: `Does this email satisfy the following criterion: ${criterion}` }])) }; - if (config.model) payload.model = config.model; - return payload; -} -export function parseResponse(result) { return parseAnswer(result, 'match'); } -export function parseBatchResponse(result, questions) { - return questions.map(({ id }) => parseAnswer(result, id)); -} -function parseAnswer(result, id) { - const answer = result?.answers?.[id]; - if (answer?.type !== 'noul' || typeof answer.noul !== 'number' || - !Number.isFinite(answer.noul) || answer.noul < 0 || answer.noul > 1) { - throw new Error(`SystemOne response must contain answers.${id} with type noul and a probability from 0 to 1.`); - } - return { matched: null, reason: null, probability: answer.noul }; -} diff --git a/modules/classificationConfig.js b/modules/classificationConfig.js deleted file mode 100644 index d6dbb5a..0000000 --- a/modules/classificationConfig.js +++ /dev/null @@ -1,39 +0,0 @@ -import { DEFAULT_AI_PARAMS } from './defaultParams.js'; -export const CONFIG_DEFAULTS = { - apiType: 'chat-completions', endpoint: 'http://127.0.0.1:5000', model: '', - apiKey: '', openaiOrganization: '', openaiProject: '', customSystemPrompt: '', - systemOneProcessAll: true, systemOneBatchSize: 8, - decisionThreshold: 0.5, inputCharacterLimit: 3686, aiParams: DEFAULT_AI_PARAMS, - htmlToMarkdown: false, stripUrlParams: false, altTextImages: false, - collapseWhitespace: false, tokenReduction: false, debugLogging: false -}; -export function validateThreshold(value) { - if (typeof value !== 'number' || !Number.isFinite(value) || value < 0 || value > 1) { - throw new Error('Match threshold must be between 0% and 100%.'); - } - return value; -} -export function validateSettings(data) { - if (data.systemOneProcessAll !== undefined && typeof data.systemOneProcessAll !== 'boolean') { - throw new Error('Process all must be a boolean.'); - } - if (data.systemOneBatchSize !== undefined && (!Number.isSafeInteger(data.systemOneBatchSize) || data.systemOneBatchSize < 1)) { - throw new Error('Rules per request must be a positive whole number.'); - } - if (data.apiType !== undefined && !['chat-completions', 'systemone'].includes(data.apiType)) throw new Error('Unknown API type.'); - if (data.decisionThreshold !== undefined) validateThreshold(data.decisionThreshold); - if (data.inputCharacterLimit !== undefined && (!Number.isSafeInteger(data.inputCharacterLimit) || data.inputCharacterLimit < 1)) { - throw new Error('Input character limit must be a positive integer.'); - } - if (data.aiRules !== undefined) { - if (!Array.isArray(data.aiRules)) throw new Error('Rules must be an array.'); - for (const rule of data.aiRules) { - if (rule.decisionThreshold !== undefined) validateThreshold(rule.decisionThreshold); - } - } -} -export function migratedInputLimit(data) { - if (data.inputCharacterLimit !== undefined) return data.inputCharacterLimit; - const value = Math.floor(Number(data.aiParams?.max_tokens ?? 4096) * 0.9); - return Number.isSafeInteger(value) && value > 0 ? value : 3686; -} diff --git a/options/dataTransfer.js b/options/dataTransfer.js index 298974c..b289c02 100644 --- a/options/dataTransfer.js +++ b/options/dataTransfer.js @@ -1,16 +1,10 @@ "use strict"; -import { validateSettings, migratedInputLimit } from '../modules/classificationConfig.js'; -import { validCacheEntry } from '../modules/AiClassifier.js'; const storage = (globalThis.messenger ?? browser).storage; const KEY_GROUPS = { settings: [ - 'systemOneProcessAll', 'systemOneBatchSize', - 'apiType', 'decisionThreshold', 'inputCharacterLimit', 'tokenReduction', 'endpoint', - 'model', - 'apiKey', - 'openaiOrganization', - 'openaiProject', + 'templateName', + 'customTemplate', 'customSystemPrompt', 'aiParams', 'debugLogging', @@ -40,15 +34,12 @@ export async function exportData(categories) { URL.revokeObjectURL(url); } -export async function importData(file, categories = Object.keys(KEY_GROUPS)) { +export async function importData(file, categories) { const text = await file.text(); const parsed = JSON.parse(text); const data = {}; for (const key of collectKeys(categories)) { if (key in parsed) data[key] = parsed[key]; } - if (categories.includes('settings') && data.inputCharacterLimit === undefined) data.inputCharacterLimit = migratedInputLimit(data); - validateSettings(data); - if (data.aiCache !== undefined) data.aiCache = Object.fromEntries(Object.entries(data.aiCache || {}).filter(([key, entry]) => validCacheEntry(key, entry))); await storage.local.set(data); } diff --git a/options/options.html b/options/options.html index 2ab0c8a..57f407c 100644 --- a/options/options.html +++ b/options/options.html @@ -31,10 +31,6 @@ .tag { --bulma-tag-h: 318; } - #diff-display { - white-space: pre-wrap; - font-family: monospace; - } @@ -51,8 +47,6 @@
  • Settings
  • Rules
  • Maintenance
  • - - @@ -64,55 +58,33 @@ - -

    Settings

    -
    - -
    -
    -
    - -

    Group all eligible, uncached rules for each email into one request. Actions still follow rule order and stop-after-match.

    -
    -
    - - -

    Turn off Process all to limit each request. Use 1 for one rule at a time.

    -
    -
    - - -

    Match when probability is at least this value. Rules may override it. Evaluate thresholds on your own email examples.

    -
    -

    - -
    -
    -
    - -
    -
    -
    - + +
    +
    +
    -

    +
    + +
    @@ -147,32 +119,6 @@
    - diff --git a/options/options.js b/options/options.js index 124d163..096f1a8 100644 --- a/options/options.js +++ b/options/options.js @@ -5,30 +5,20 @@ document.addEventListener('DOMContentLoaded', async () => { const dataTransfer = await import(browser.runtime.getURL('options/dataTransfer.js')); const { detectSystemTheme } = await import(browser.runtime.getURL('modules/themeUtils.js')); const { DEFAULT_AI_PARAMS } = await import(browser.runtime.getURL('modules/defaultParams.js')); - const { validateSettings, migratedInputLimit } = await import(browser.runtime.getURL('modules/classificationConfig.js')); const defaults = await storage.local.get([ - 'systemOneProcessAll', 'systemOneBatchSize', - 'apiType', 'decisionThreshold', 'inputCharacterLimit', 'endpoint', + 'templateName', + 'customTemplate', 'customSystemPrompt', - 'model', - 'apiKey', - 'openaiOrganization', - 'openaiProject', 'aiParams', 'debugLogging', 'htmlToMarkdown', 'stripUrlParams', 'altTextImages', 'collapseWhitespace', - 'tokenReduction', 'aiRules', 'aiCache', - 'theme', - 'showDebugTab', - 'lastPayload', - 'lastFullText', - 'lastPromptText' + 'theme' ]); const tabButtons = document.querySelectorAll('#main-tabs li'); const tabs = document.querySelectorAll('.tab-content'); @@ -73,201 +63,36 @@ document.addEventListener('DOMContentLoaded', async () => { } await applyTheme(themeSelect.value); - const payloadDisplay = document.getElementById('payload-display'); - const diffDisplay = document.getElementById('diff-display'); - const diffContainer = document.getElementById('diff-container'); - const promptReductionLabel = document.getElementById('prompt-reduction'); - - let lastFullText = defaults.lastFullText || ''; - let lastPromptText = defaults.lastPromptText || ''; - let lastPayload = defaults.lastPayload ? JSON.stringify(defaults.lastPayload, null, 2) : ''; - - if (lastPayload) { - payloadDisplay.textContent = lastPayload; - } themeSelect.addEventListener('change', async () => { markDirty(); await applyTheme(themeSelect.value); }); - const apiTypeInput = document.getElementById('api-type'); - apiTypeInput.value = defaults.apiType || 'chat-completions'; - const processAllInput = document.getElementById('systemone-process-all'); - const batchSizeInput = document.getElementById('systemone-batch-size'); - processAllInput.checked = defaults.systemOneProcessAll ?? true; - let savedBatchSize = defaults.systemOneBatchSize ?? 8; - batchSizeInput.value = savedBatchSize; - function updateBatchControls() { - batchSizeInput.disabled = processAllInput.checked || apiTypeInput.value !== 'systemone'; + document.getElementById('endpoint').value = defaults.endpoint || 'http://127.0.0.1:5000/v1/completions'; + + const templates = { + openai: browser.i18n.getMessage('template.openai'), + qwen: browser.i18n.getMessage('template.qwen'), + mistral: browser.i18n.getMessage('template.mistral'), + custom: browser.i18n.getMessage('template.custom') + }; + const templateSelect = document.getElementById('template'); + for (const [value, label] of Object.entries(templates)) { + const opt = document.createElement('option'); + opt.value = value; + opt.textContent = label; + templateSelect.appendChild(opt); } - processAllInput.addEventListener('change', updateBatchControls); - const thresholdInput = document.getElementById('decision-threshold'); - thresholdInput.value = (defaults.decisionThreshold ?? 0.5) * 100; - const inputLimit = document.getElementById('input-character-limit'); - inputLimit.value = migratedInputLimit(defaults); - const settingsError = document.getElementById('settings-error'); - function updateApiControls() { - const decision = apiTypeInput.value === 'systemone'; - updateBatchControls(); - document.querySelectorAll('.systemone-only').forEach(el => el.classList.toggle('is-hidden', !decision)); - for (const id of ['system-instructions', 'openai-organization', 'openai-project', ...Object.keys(DEFAULT_AI_PARAMS)]) { - document.getElementById(id)?.closest('.field')?.classList.toggle('is-hidden', decision); - } - document.getElementById('reset-system').classList.toggle('is-hidden', decision); - updateEndpointPreview(); + templateSelect.value = defaults.templateName || 'openai'; + + const customBox = document.getElementById('custom-template-container'); + const customTemplate = document.getElementById('custom-template'); + customTemplate.value = defaults.customTemplate || ''; + + function updateVisibility() { + customBox.classList.toggle('is-hidden', templateSelect.value !== 'custom'); } - apiTypeInput.addEventListener('change', updateApiControls); - const endpointInput = document.getElementById('endpoint'); - const endpointPreview = document.getElementById('endpoint-preview'); - const fallbackEndpoint = 'http://127.0.0.1:5000'; - const storedEndpoint = defaults.endpoint || fallbackEndpoint; - const endpointBase = AiClassifier.normalizeEndpointBase(storedEndpoint) || storedEndpoint; - endpointInput.value = endpointBase; - - function updateEndpointPreview() { - const resolved = AiClassifier.buildEndpointUrl(endpointInput.value, apiTypeInput.value); - endpointPreview.textContent = resolved - ? `Resolved endpoint: ${resolved}` - : 'Resolved endpoint: (invalid)'; - } - endpointInput.addEventListener('input', updateEndpointPreview); - updateApiControls(); - - const modelSelect = document.getElementById('model-select'); - const refreshModelsBtn = document.getElementById('refresh-models'); - const modelHelp = document.getElementById('model-help'); - const storedModel = typeof defaults.model === 'string' ? defaults.model : ''; - - function setModelHelp(message = '', isError = false) { - if (!modelHelp) return; - modelHelp.textContent = message; - modelHelp.classList.toggle('is-danger', isError); - } - - function populateModelOptions(models = [], selectedModel = '') { - if (!modelSelect) return; - const modelIds = Array.isArray(models) ? models.filter(Boolean) : []; - modelSelect.innerHTML = ''; - - const noneOpt = document.createElement('option'); - noneOpt.value = ''; - noneOpt.textContent = 'None (omit model)'; - modelSelect.appendChild(noneOpt); - - if (selectedModel && !modelIds.includes(selectedModel)) { - const storedOpt = document.createElement('option'); - storedOpt.value = selectedModel; - storedOpt.textContent = `Stored: ${selectedModel}`; - modelSelect.appendChild(storedOpt); - } - - for (const id of modelIds) { - const opt = document.createElement('option'); - opt.value = id; - opt.textContent = id; - modelSelect.appendChild(opt); - } - - const hasSelected = [...modelSelect.options].some(opt => opt.value === selectedModel); - modelSelect.value = hasSelected ? selectedModel : ''; - } - - function buildAuthHeaders() { - const headers = {}; - const apiKey = apiKeyInput?.value.trim(); - if (apiKey) { - headers.Authorization = `Bearer ${apiKey}`; - } - const organization = openaiOrgInput?.value.trim(); - if (organization && apiTypeInput.value === 'chat-completions') { - headers["OpenAI-Organization"] = organization; - } - const project = openaiProjectInput?.value.trim(); - if (project && apiTypeInput.value === 'chat-completions') { - headers["OpenAI-Project"] = project; - } - return headers; - } - - async function fetchModels(preferredModel = '') { - if (!modelSelect || !refreshModelsBtn) return; - const modelsUrl = AiClassifier.buildModelsUrl(endpointInput.value); - const selectedModel = preferredModel || modelSelect.value; - if (!modelsUrl) { - logger.aiLog('[options] model refresh skipped: invalid endpoint', { level: 'warn' }, { - endpoint: endpointInput.value - }); - setModelHelp('Set a valid endpoint to load models.', true); - populateModelOptions([], selectedModel); - return; - } - - refreshModelsBtn.disabled = true; - setModelHelp('Loading models...'); - const headers = buildAuthHeaders(); - logger.aiLog('[options] loading models', {}, { - endpoint: endpointInput.value, - modelsUrl, - selectedModel, - hasAuthorization: typeof headers.Authorization === 'string', - hasOrganization: typeof headers['OpenAI-Organization'] === 'string', - hasProject: typeof headers['OpenAI-Project'] === 'string' - }); - - try { - const response = await fetch(modelsUrl, { method: 'GET', headers }); - logger.aiLog('[options] model refresh response received', {}, { - status: response.status, - ok: response.ok, - contentType: response.headers.get('content-type') || '' - }); - if (!response.ok) { - throw new Error(`HTTP ${response.status}`); - } - const data = await response.json(); - logger.aiLog('[options] model refresh payload parsed', {}, { - payloadType: Array.isArray(data) ? 'array' : typeof data, - hasDataArray: Array.isArray(data?.data), - hasModelsArray: Array.isArray(data?.models), - topLevelKeys: data && typeof data === 'object' && !Array.isArray(data) - ? Object.keys(data) - : [] - }); - let models = []; - if (Array.isArray(data?.data)) { - models = data.data.map(model => model?.id ?? model?.name ?? model?.model ?? '').filter(Boolean); - } else if (Array.isArray(data?.models)) { - models = data.models.map(model => model?.id ?? model?.name ?? model?.model ?? '').filter(Boolean); - } else if (Array.isArray(data)) { - models = data.map(model => model?.id ?? model?.name ?? model?.model ?? model).filter(Boolean); - } - models = [...new Set(models)]; - logger.aiLog('[options] model refresh parsed models', {}, { - count: models.length, - models - }); - populateModelOptions(models, selectedModel); - setModelHelp(models.length ? `Loaded ${models.length} model${models.length === 1 ? '' : 's'}.` : 'No models returned.'); - } catch (e) { - logger.aiLog('[options] failed to load models', { level: 'warn' }, e); - const message = String(e?.message || e || ''); - const isLikelyCors = e instanceof TypeError || /Failed to fetch|NetworkError|Load failed/i.test(message); - setModelHelp( - isLikelyCors - ? 'Failed to load models. The server responded, but Thunderbird may have blocked access to the response. Check CORS on the AI server and verify the endpoint is reachable from the add-on.' - : 'Failed to load models. Check the endpoint, HTTP status, and network.', - true - ); - populateModelOptions([], selectedModel); - } finally { - refreshModelsBtn.disabled = false; - } - } - - populateModelOptions([], storedModel); - refreshModelsBtn?.addEventListener('click', () => { - logger.aiLog('[options] model refresh button clicked'); - fetchModels(modelSelect.value); - }); + templateSelect.addEventListener('change', updateVisibility); + updateVisibility(); const advancedBox = document.getElementById('advanced-options'); const advancedBtn = document.getElementById('toggle-advanced'); @@ -275,26 +100,6 @@ document.addEventListener('DOMContentLoaded', async () => { advancedBox.classList.toggle('is-hidden'); }); - const apiKeyInput = document.getElementById('api-key'); - const apiKeyToggle = document.getElementById('toggle-api-key'); - const openaiOrgInput = document.getElementById('openai-organization'); - const openaiProjectInput = document.getElementById('openai-project'); - if (apiKeyInput) { - apiKeyInput.value = typeof defaults.apiKey === 'string' ? defaults.apiKey : ''; - } - if (openaiOrgInput) { - openaiOrgInput.value = typeof defaults.openaiOrganization === 'string' ? defaults.openaiOrganization : ''; - } - if (openaiProjectInput) { - openaiProjectInput.value = typeof defaults.openaiProject === 'string' ? defaults.openaiProject : ''; - } - apiKeyToggle?.addEventListener('click', () => { - if (!apiKeyInput) return; - const show = apiKeyInput.type === 'password'; - apiKeyInput.type = show ? 'text' : 'password'; - apiKeyToggle.textContent = show ? 'Hide' : 'Show'; - }); - const debugToggle = document.getElementById('debug-logging'); debugToggle.checked = defaults.debugLogging === true; @@ -310,144 +115,6 @@ document.addEventListener('DOMContentLoaded', async () => { const collapseWhitespaceToggle = document.getElementById('collapse-whitespace'); collapseWhitespaceToggle.checked = defaults.collapseWhitespace === true; - const tokenReductionToggle = document.getElementById('token-reduction'); - tokenReductionToggle.checked = defaults.tokenReduction === true; - - function tokenSavingEnabled() { - return htmlToggle.checked - || stripUrlToggle.checked - || altTextToggle.checked - || collapseWhitespaceToggle.checked - || tokenReductionToggle.checked; - } - - function updatePromptReductionLabel(hasDiff) { - if (!promptReductionLabel) return; - if (!hasDiff || !tokenSavingEnabled() || !lastFullText || !lastPromptText) { - promptReductionLabel.classList.add('is-hidden'); - return; - } - const baseLength = lastFullText.length; - const promptLength = lastPromptText.length; - const percentSaved = baseLength > 0 - ? Math.max(0, Math.round((1 - (promptLength / baseLength)) * 100)) - : 0; - promptReductionLabel.textContent = `Prompt Token Reduction: ${percentSaved}%`; - promptReductionLabel.classList.remove('is-hidden'); - } - - function updateDiffDisplay() { - if (lastFullText && lastPromptText && diff_match_patch) { - const dmp = new diff_match_patch(); - dmp.Diff_EditCost = 4; - const diffs = dmp.diff_main(lastFullText, lastPromptText); - dmp.diff_cleanupEfficiency(diffs); - const hasDiff = diffs.some(d => d[0] !== 0); - if (hasDiff) { - diffDisplay.innerHTML = dmp.diff_prettyHtml(diffs); - diffContainer.classList.remove('is-hidden'); - } else { - diffDisplay.innerHTML = ''; - diffContainer.classList.add('is-hidden'); - } - updatePromptReductionLabel(hasDiff); - } else { - diffDisplay.innerHTML = ''; - diffContainer.classList.add('is-hidden'); - updatePromptReductionLabel(false); - } - } - - const debugTabToggle = document.getElementById('show-debug-tab'); - const debugTabBtn = document.getElementById('debug-tab-button'); - const errorTabBtn = document.getElementById('errors-tab-button'); - const errorsEmpty = document.getElementById('errors-empty'); - const errorsPanel = document.getElementById('errors-panel'); - const errorsList = document.getElementById('errors-list'); - const errorsCount = document.getElementById('errors-count'); - function updateDebugTab() { - const visible = debugTabToggle.checked; - debugTabBtn.classList.toggle('is-hidden', !visible); - } - debugTabToggle.checked = defaults.showDebugTab === true; - debugTabToggle.addEventListener('change', () => { updateDebugTab(); markDirty(); }); - updateDebugTab(); - - function formatErrorTime(value) { - try { - return new Date(value).toLocaleString(); - } catch (e) { - return ''; - } - } - - function renderErrors(entries = []) { - const hasErrors = entries.length > 0; - errorTabBtn.classList.toggle('is-hidden', !hasErrors); - errorsEmpty.classList.toggle('is-hidden', hasErrors); - errorsPanel.classList.toggle('is-hidden', !hasErrors); - errorsList.innerHTML = ''; - errorsCount.textContent = String(entries.length); - if (!hasErrors) { - return; - } - entries.forEach(entry => { - const card = document.createElement('article'); - card.className = 'message is-danger is-light mb-4'; - const header = document.createElement('div'); - header.className = 'message-header'; - const title = document.createElement('p'); - title.textContent = entry.context || 'Error'; - const time = document.createElement('span'); - time.className = 'is-size-7 has-text-weight-normal'; - time.textContent = formatErrorTime(entry.time); - header.appendChild(title); - header.appendChild(time); - const body = document.createElement('div'); - body.className = 'message-body'; - const summary = document.createElement('p'); - summary.className = 'mb-2'; - summary.textContent = entry.message || 'Unknown error'; - body.appendChild(summary); - if (entry.detail) { - const detail = document.createElement('pre'); - detail.className = 'is-family-monospace is-size-7'; - detail.textContent = entry.detail; - body.appendChild(detail); - } - card.appendChild(header); - card.appendChild(body); - errorsList.appendChild(card); - }); - } - - async function loadErrors() { - try { - const response = await browser.runtime.sendMessage({ type: 'sortana:getErrorLog' }); - renderErrors(response?.errors || []); - } catch (e) { - renderErrors([]); - } - } - - browser.runtime.onMessage.addListener((msg) => { - if (msg?.type === 'sortana:errorLogUpdated') { - loadErrors(); - } - }); - - await loadErrors(); - - updateDiffDisplay(); - await fetchModels(storedModel); - - [htmlToggle, stripUrlToggle, altTextToggle, collapseWhitespaceToggle, tokenReductionToggle].forEach(toggle => { - toggle.addEventListener('change', () => { - updatePromptReductionLabel(!diffContainer.classList.contains('is-hidden')); - }); - }); - - const aiParams = Object.assign({}, DEFAULT_AI_PARAMS, defaults.aiParams || {}); for (const [key, val] of Object.entries(aiParams)) { const el = document.getElementById(key); @@ -497,7 +164,7 @@ document.addEventListener('DOMContentLoaded', async () => { const perDayEl = document.getElementById('per-day'); let timingLogged = false; ruleCountEl.textContent = (defaults.aiRules || []).length; - cacheCountEl.textContent = '…'; + cacheCountEl.textContent = defaults.aiCache ? Object.keys(defaults.aiCache).length : 0; function createActionRow(action = {type: 'tag'}) { const row = document.createElement('div'); @@ -891,25 +558,14 @@ document.addEventListener('DOMContentLoaded', async () => { body.appendChild(folderBox); article.appendChild(header); - const thresholdField = document.createElement('label'); - thresholdField.className = 'field systemone-only'; - thresholdField.classList.toggle('is-hidden', apiTypeInput.value !== 'systemone'); - thresholdField.textContent = 'Match probability threshold (%) — blank uses default'; - const override = document.createElement('input'); - override.className = 'input decision-threshold'; - override.type = 'number'; - override.min = '0'; override.max = '100'; override.step = 'any'; - override.value = rule.decisionThreshold === undefined ? '' : rule.decisionThreshold * 100; - thresholdField.appendChild(override); - body.appendChild(thresholdField); article.appendChild(body); rulesContainer.appendChild(article); } } - function readRules() { - return [...rulesContainer.querySelectorAll('.rule')].map(ruleEl => { + addRuleBtn.addEventListener('click', () => { + const data = [...rulesContainer.querySelectorAll('.rule')].map(ruleEl => { const criterion = ruleEl.querySelector('.criterion').value; const actions = [...ruleEl.querySelectorAll('.action-row')].map(row => { const type = row.querySelector('select').value; @@ -931,11 +587,8 @@ document.addEventListener('DOMContentLoaded', async () => { if (type === 'flag') { return { type, flagged: row.querySelector('.flag-select').value === 'true' }; } - if (type === 'forward') { - return { type, address: row.querySelector('.forward-input').value.trim() }; - } - if (type === 'reply') { - return { type, replyType: row.querySelector('.reply-select').value }; + if (type === 'delete' || type === 'archive') { + return { type }; } return { type }; }); @@ -947,8 +600,6 @@ document.addEventListener('DOMContentLoaded', async () => { const accounts = [...(ruleEl.querySelector('.account-select')?.selectedOptions || [])].map(o => o.value); const folders = [...(ruleEl.querySelector('.folder-filter-select')?.selectedOptions || [])].map(o => o.value); const rule = { criterion, actions, enabled }; - const override = ruleEl.querySelector('.decision-threshold').value; - if (override.trim() !== '') rule.decisionThreshold = Number(override) / 100; if (unreadOnly) rule.unreadOnly = true; if (stopProcessing) rule.stopProcessing = true; if (!isNaN(minAgeDays)) rule.minAgeDays = minAgeDays; @@ -957,9 +608,6 @@ document.addEventListener('DOMContentLoaded', async () => { if (folders.length) rule.folders = folders; return rule; }); - } - addRuleBtn.addEventListener('click', () => { - const data = readRules(); data.push({ criterion: '', actions: [], unreadOnly: false, stopProcessing: false, enabled: true, accounts: [], folders: [] }); renderRules(data); }); @@ -976,7 +624,6 @@ document.addEventListener('DOMContentLoaded', async () => { if (r.moveTo) actions.push({ type: 'move', folder: r.moveTo }); if (r.copyTarget || r.copyTo) actions.push({ type: 'copy', copyTarget: r.copyTarget || r.copyTo }); const rule = { criterion: r.criterion, actions }; - if (r.decisionThreshold !== undefined) rule.decisionThreshold = r.decisionThreshold; if (r.stopProcessing) rule.stopProcessing = true; if (r.unreadOnly) rule.unreadOnly = true; if (typeof r.minAgeDays === 'number') rule.minAgeDays = r.minAgeDays; @@ -1046,27 +693,11 @@ document.addEventListener('DOMContentLoaded', async () => { } try { - const { count } = await browser.runtime.sendMessage({ type: 'sortana:getCacheSize' }); - cacheCountEl.textContent = count; + const { aiCache } = await storage.local.get('aiCache'); + cacheCountEl.textContent = aiCache ? Object.keys(aiCache).length : 0; } catch { cacheCountEl.textContent = '?'; } - - try { - if (debugTabToggle.checked) { - const latest = await storage.local.get(['lastPayload', 'lastFullText', 'lastPromptText']); - const payloadStr = latest.lastPayload ? JSON.stringify(latest.lastPayload, null, 2) : ''; - if (payloadStr !== lastPayload) { - lastPayload = payloadStr; - payloadDisplay.textContent = payloadStr; - } - if (latest.lastFullText !== lastFullText || latest.lastPromptText !== lastPromptText) { - lastFullText = latest.lastFullText || ''; - lastPromptText = latest.lastPromptText || ''; - updateDiffDisplay(); - } - } - } catch {} } refreshMaintenance(); @@ -1077,11 +708,6 @@ document.addEventListener('DOMContentLoaded', async () => { cacheCountEl.textContent = '0'; }); - document.getElementById('reset-timing').addEventListener('click', async () => { - await browser.runtime.sendMessage({ type: 'sortana:resetTimingStats' }); - await refreshMaintenance(); - }); - function selectedCategories() { return [...document.querySelectorAll('.transfer-category:checked')].map(el => el.value); } @@ -1094,35 +720,17 @@ document.addEventListener('DOMContentLoaded', async () => { document.getElementById('import-data').addEventListener('click', () => importInput.click()); importInput.addEventListener('change', async () => { if (importInput.files.length) { - try { - await dataTransfer.importData(importInput.files[0], selectedCategories()); - location.reload(); - } catch (error) { - window.alert(`Import failed: ${error.message}`); - } + await dataTransfer.importData(importInput.files[0], selectedCategories()); + location.reload(); } }); initialized = true; document.getElementById('save').addEventListener('click', async () => { - settingsError.textContent = ''; - const apiType = apiTypeInput.value; - const systemOneProcessAll = processAllInput.checked; - const enteredBatchSize = Number(batchSizeInput.value); - const validBatchSize = Number.isSafeInteger(enteredBatchSize) && enteredBatchSize > 0; - if (!batchSizeInput.disabled && !validBatchSize) { - settingsError.textContent = 'Rules per request must be a positive whole number.'; - return; - } - const systemOneBatchSize = validBatchSize ? enteredBatchSize : savedBatchSize; - const decisionThreshold = thresholdInput.value.trim() === '' ? NaN : Number(thresholdInput.value) / 100; - const inputCharacterLimit = Number(inputLimit.value); - const endpoint = endpointInput.value.trim(); - const model = modelSelect?.value || ''; - const apiKey = apiKeyInput?.value.trim() || ''; - const openaiOrganization = openaiOrgInput?.value.trim() || ''; - const openaiProject = openaiProjectInput?.value.trim() || ''; + const endpoint = document.getElementById('endpoint').value; + const templateName = templateSelect.value; + const customTemplateText = customTemplate.value; const customSystemPrompt = systemBox.value; const aiParamsSave = {}; for (const key of Object.keys(DEFAULT_AI_PARAMS)) { @@ -1134,27 +742,60 @@ document.addEventListener('DOMContentLoaded', async () => { } const debugLogging = debugToggle.checked; const htmlToMarkdown = htmlToggle.checked; - const invalidThreshold = [...document.querySelectorAll('.decision-threshold'), thresholdInput, inputLimit].find(el => !el.checkValidity()); - if (invalidThreshold) { - settingsError.textContent = 'Enter thresholds from 0% to 100% and a positive whole-number character limit.'; - return; - } - const rules = readRules().filter(r => r.criterion); + const rules = [...rulesContainer.querySelectorAll('.rule')].map(ruleEl => { + const criterion = ruleEl.querySelector('.criterion').value; + const actions = [...ruleEl.querySelectorAll('.action-row')].map(row => { + const type = row.querySelector('select').value; + if (type === 'tag') { + return { type, tagKey: row.querySelector('.tag-select').value }; + } + if (type === 'move') { + return { type, folder: row.querySelector('.folder-select').value }; + } + if (type === 'copy') { + return { type, copyTarget: row.querySelector('.folder-select').value }; + } + if (type === 'junk') { + return { type, junk: row.querySelector('.junk-select').value === 'true' }; + } + if (type === 'read') { + return { type, read: row.querySelector('.read-select').value === 'true' }; + } + if (type === 'flag') { + return { type, flagged: row.querySelector('.flag-select').value === 'true' }; + } + if (type === 'forward') { + return { type, address: row.querySelector('.forward-input').value.trim() }; + } + if (type === 'reply') { + return { type, replyType: row.querySelector('.reply-select').value }; + } + return { type }; + }); + const stopProcessing = ruleEl.querySelector('.stop-processing')?.checked; + const unreadOnly = ruleEl.querySelector('.unread-only')?.checked; + const enabled = ruleEl.dataset.enabled !== 'false'; + const minAgeDays = parseFloat(ruleEl.querySelector('.min-age')?.value); + const maxAgeDays = parseFloat(ruleEl.querySelector('.max-age')?.value); + const accounts = [...(ruleEl.querySelector('.account-select')?.selectedOptions || [])].map(o => o.value); + const folders = [...(ruleEl.querySelector('.folder-filter-select')?.selectedOptions || [])].map(o => o.value); + const rule = { criterion, actions, enabled }; + if (unreadOnly) rule.unreadOnly = true; + if (stopProcessing) rule.stopProcessing = true; + if (!isNaN(minAgeDays)) rule.minAgeDays = minAgeDays; + if (!isNaN(maxAgeDays)) rule.maxAgeDays = maxAgeDays; + if (accounts.length) rule.accounts = accounts; + if (folders.length) rule.folders = folders; + return rule; + }).filter(r => r.criterion); const stripUrlParams = stripUrlToggle.checked; const altTextImages = altTextToggle.checked; const collapseWhitespace = collapseWhitespaceToggle.checked; - const tokenReduction = tokenReductionToggle.checked; - const showDebugTab = debugTabToggle.checked; const theme = themeSelect.value; - try { validateSettings({ systemOneProcessAll, systemOneBatchSize, apiType, decisionThreshold, inputCharacterLimit, aiRules: rules }); } - catch (error) { settingsError.textContent = error.message; return; } - await storage.local.set({ systemOneProcessAll, systemOneBatchSize, apiType, decisionThreshold, inputCharacterLimit, endpoint, model, apiKey, openaiOrganization, openaiProject, customSystemPrompt, aiParams: aiParamsSave, debugLogging, htmlToMarkdown, stripUrlParams, altTextImages, collapseWhitespace, tokenReduction, aiRules: rules, theme, showDebugTab }); - savedBatchSize = systemOneBatchSize; - batchSizeInput.value = savedBatchSize; - await storage.local.remove(['templateName', 'customTemplate']); + await storage.local.set({ endpoint, templateName, customTemplate: customTemplateText, customSystemPrompt, aiParams: aiParamsSave, debugLogging, htmlToMarkdown, stripUrlParams, altTextImages, collapseWhitespace, aiRules: rules, theme }); await applyTheme(theme); try { - await AiClassifier.setConfig({ systemOneProcessAll, systemOneBatchSize, apiType, decisionThreshold, inputCharacterLimit, endpoint, model, apiKey, openaiOrganization, openaiProject, customSystemPrompt, aiParams: aiParamsSave, debugLogging }); + await AiClassifier.setConfig({ endpoint, templateName, customTemplate: customTemplateText, customSystemPrompt, aiParams: aiParamsSave, debugLogging }); logger.setDebug(debugLogging); } catch (e) { logger.aiLog('[options] failed to apply config', {level: 'error'}, e); diff --git a/prompt_templates/mistral.txt b/prompt_templates/mistral.txt new file mode 100644 index 0000000..f78bed7 --- /dev/null +++ b/prompt_templates/mistral.txt @@ -0,0 +1,12 @@ +[INST] {{system}} + +Email: +{{email}} + +Criterion: {{query}} +Remember, return ONLY a JSON object on a single line of the form: +{"match": true} - if the email satisfies the criterion +{"match": false} - otherwise + +Do not add any other keys, text, or formatting. +[/INST] diff --git a/prompt_templates/openai.txt b/prompt_templates/openai.txt new file mode 100644 index 0000000..bf7cea1 --- /dev/null +++ b/prompt_templates/openai.txt @@ -0,0 +1,14 @@ +<|im_start|>system +{{system}}<|im_end|> +<|im_start|>user +**Email Contents** +``` +{{email}} +``` +Classification Criterion: {{query}} +Remember, return ONLY a JSON object on a single line of the form: +{"match": true} - if the email satisfies the criterion +{"match": false} - otherwise + +Do not add any other keys, text, or formatting.<|im_end|> +<|im_start|>assistant diff --git a/prompt_templates/qwen.txt b/prompt_templates/qwen.txt new file mode 100644 index 0000000..0c25472 --- /dev/null +++ b/prompt_templates/qwen.txt @@ -0,0 +1,15 @@ +<|im_start|>system +{{system}} +<|im_end|> +<|im_start|>user +Email: +{{email}} + +Criterion: {{query}} +Remember, return ONLY a JSON object on a single line of the form: +{"match": true} - if the email satisfies the criterion +{"match": false} - otherwise + +Do not add any other keys, text, or formatting. +<|im_end|> +<|im_start|>assistant diff --git a/resources/img/circledot-dark-16.png b/resources/img/circledot-dark-16.png deleted file mode 100644 index db602ab..0000000 Binary files a/resources/img/circledot-dark-16.png and /dev/null differ diff --git a/resources/img/circledot-dark-32.png b/resources/img/circledot-dark-32.png deleted file mode 100644 index d29ac16..0000000 Binary files a/resources/img/circledot-dark-32.png and /dev/null differ diff --git a/resources/img/circledot-dark-64.png b/resources/img/circledot-dark-64.png deleted file mode 100644 index f29bb77..0000000 Binary files a/resources/img/circledot-dark-64.png and /dev/null differ diff --git a/resources/img/circledot-light-16.png b/resources/img/circledot-light-16.png deleted file mode 100644 index 4809c5a..0000000 Binary files a/resources/img/circledot-light-16.png and /dev/null differ diff --git a/resources/img/circledot-light-32.png b/resources/img/circledot-light-32.png deleted file mode 100644 index 06c342f..0000000 Binary files a/resources/img/circledot-light-32.png and /dev/null differ diff --git a/resources/img/circledot-light-64.png b/resources/img/circledot-light-64.png deleted file mode 100644 index cb8634a..0000000 Binary files a/resources/img/circledot-light-64.png and /dev/null differ diff --git a/resources/js/diff_match_patch_uncompressed.js b/resources/js/diff_match_patch_uncompressed.js deleted file mode 100644 index 88a702c..0000000 --- a/resources/js/diff_match_patch_uncompressed.js +++ /dev/null @@ -1,2236 +0,0 @@ -/** - * Diff Match and Patch - * Copyright 2018 The diff-match-patch Authors. - * https://github.com/google/diff-match-patch - * - * Licensed under the Apache License, Version 2.0 (the "License"); - * you may not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -/** - * @fileoverview Computes the difference between two texts to create a patch. - * Applies the patch onto another text, allowing for errors. - * @author fraser@google.com (Neil Fraser) - */ - -/** - * Class containing the diff, match and patch methods. - * @constructor - */ -var diff_match_patch = function() { - - // Defaults. - // Redefine these in your program to override the defaults. - - // Number of seconds to map a diff before giving up (0 for infinity). - this.Diff_Timeout = 1.0; - // Cost of an empty edit operation in terms of edit characters. - this.Diff_EditCost = 4; - // At what point is no match declared (0.0 = perfection, 1.0 = very loose). - this.Match_Threshold = 0.5; - // How far to search for a match (0 = exact location, 1000+ = broad match). - // A match this many characters away from the expected location will add - // 1.0 to the score (0.0 is a perfect match). - this.Match_Distance = 1000; - // When deleting a large block of text (over ~64 characters), how close do - // the contents have to be to match the expected contents. (0.0 = perfection, - // 1.0 = very loose). Note that Match_Threshold controls how closely the - // end points of a delete need to match. - this.Patch_DeleteThreshold = 0.5; - // Chunk size for context length. - this.Patch_Margin = 4; - - // The number of bits in an int. - this.Match_MaxBits = 32; -}; - - -// DIFF FUNCTIONS - - -/** - * The data structure representing a diff is an array of tuples: - * [[DIFF_DELETE, 'Hello'], [DIFF_INSERT, 'Goodbye'], [DIFF_EQUAL, ' world.']] - * which means: delete 'Hello', add 'Goodbye' and keep ' world.' - */ -var DIFF_DELETE = -1; -var DIFF_INSERT = 1; -var DIFF_EQUAL = 0; - -/** - * Class representing one diff tuple. - * Attempts to look like a two-element array (which is what this used to be). - * @param {number} op Operation, one of: DIFF_DELETE, DIFF_INSERT, DIFF_EQUAL. - * @param {string} text Text to be deleted, inserted, or retained. - * @constructor - */ -diff_match_patch.Diff = function(op, text) { - this[0] = op; - this[1] = text; -}; - -diff_match_patch.Diff.prototype.length = 2; - -/** - * Emulate the output of a two-element array. - * @return {string} Diff operation as a string. - */ -diff_match_patch.Diff.prototype.toString = function() { - return this[0] + ',' + this[1]; -}; - - -/** - * Find the differences between two texts. Simplifies the problem by stripping - * any common prefix or suffix off the texts before diffing. - * @param {string} text1 Old string to be diffed. - * @param {string} text2 New string to be diffed. - * @param {boolean=} opt_checklines Optional speedup flag. If present and false, - * then don't run a line-level diff first to identify the changed areas. - * Defaults to true, which does a faster, slightly less optimal diff. - * @param {number=} opt_deadline Optional time when the diff should be complete - * by. Used internally for recursive calls. Users should set DiffTimeout - * instead. - * @return {!Array.} Array of diff tuples. - */ -diff_match_patch.prototype.diff_main = function(text1, text2, opt_checklines, - opt_deadline) { - // Set a deadline by which time the diff must be complete. - if (typeof opt_deadline == 'undefined') { - if (this.Diff_Timeout <= 0) { - opt_deadline = Number.MAX_VALUE; - } else { - opt_deadline = (new Date).getTime() + this.Diff_Timeout * 1000; - } - } - var deadline = opt_deadline; - - // Check for null inputs. - if (text1 == null || text2 == null) { - throw new Error('Null input. (diff_main)'); - } - - // Check for equality (speedup). - if (text1 == text2) { - if (text1) { - return [new diff_match_patch.Diff(DIFF_EQUAL, text1)]; - } - return []; - } - - if (typeof opt_checklines == 'undefined') { - opt_checklines = true; - } - var checklines = opt_checklines; - - // Trim off common prefix (speedup). - var commonlength = this.diff_commonPrefix(text1, text2); - var commonprefix = text1.substring(0, commonlength); - text1 = text1.substring(commonlength); - text2 = text2.substring(commonlength); - - // Trim off common suffix (speedup). - commonlength = this.diff_commonSuffix(text1, text2); - var commonsuffix = text1.substring(text1.length - commonlength); - text1 = text1.substring(0, text1.length - commonlength); - text2 = text2.substring(0, text2.length - commonlength); - - // Compute the diff on the middle block. - var diffs = this.diff_compute_(text1, text2, checklines, deadline); - - // Restore the prefix and suffix. - if (commonprefix) { - diffs.unshift(new diff_match_patch.Diff(DIFF_EQUAL, commonprefix)); - } - if (commonsuffix) { - diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, commonsuffix)); - } - this.diff_cleanupMerge(diffs); - return diffs; -}; - - -/** - * Find the differences between two texts. Assumes that the texts do not - * have any common prefix or suffix. - * @param {string} text1 Old string to be diffed. - * @param {string} text2 New string to be diffed. - * @param {boolean} checklines Speedup flag. If false, then don't run a - * line-level diff first to identify the changed areas. - * If true, then run a faster, slightly less optimal diff. - * @param {number} deadline Time when the diff should be complete by. - * @return {!Array.} Array of diff tuples. - * @private - */ -diff_match_patch.prototype.diff_compute_ = function(text1, text2, checklines, - deadline) { - var diffs; - - if (!text1) { - // Just add some text (speedup). - return [new diff_match_patch.Diff(DIFF_INSERT, text2)]; - } - - if (!text2) { - // Just delete some text (speedup). - return [new diff_match_patch.Diff(DIFF_DELETE, text1)]; - } - - var longtext = text1.length > text2.length ? text1 : text2; - var shorttext = text1.length > text2.length ? text2 : text1; - var i = longtext.indexOf(shorttext); - if (i != -1) { - // Shorter text is inside the longer text (speedup). - diffs = [new diff_match_patch.Diff(DIFF_INSERT, longtext.substring(0, i)), - new diff_match_patch.Diff(DIFF_EQUAL, shorttext), - new diff_match_patch.Diff(DIFF_INSERT, - longtext.substring(i + shorttext.length))]; - // Swap insertions for deletions if diff is reversed. - if (text1.length > text2.length) { - diffs[0][0] = diffs[2][0] = DIFF_DELETE; - } - return diffs; - } - - if (shorttext.length == 1) { - // Single character string. - // After the previous speedup, the character can't be an equality. - return [new diff_match_patch.Diff(DIFF_DELETE, text1), - new diff_match_patch.Diff(DIFF_INSERT, text2)]; - } - - // Check to see if the problem can be split in two. - var hm = this.diff_halfMatch_(text1, text2); - if (hm) { - // A half-match was found, sort out the return data. - var text1_a = hm[0]; - var text1_b = hm[1]; - var text2_a = hm[2]; - var text2_b = hm[3]; - var mid_common = hm[4]; - // Send both pairs off for separate processing. - var diffs_a = this.diff_main(text1_a, text2_a, checklines, deadline); - var diffs_b = this.diff_main(text1_b, text2_b, checklines, deadline); - // Merge the results. - return diffs_a.concat([new diff_match_patch.Diff(DIFF_EQUAL, mid_common)], - diffs_b); - } - - if (checklines && text1.length > 100 && text2.length > 100) { - return this.diff_lineMode_(text1, text2, deadline); - } - - return this.diff_bisect_(text1, text2, deadline); -}; - - -/** - * Do a quick line-level diff on both strings, then rediff the parts for - * greater accuracy. - * This speedup can produce non-minimal diffs. - * @param {string} text1 Old string to be diffed. - * @param {string} text2 New string to be diffed. - * @param {number} deadline Time when the diff should be complete by. - * @return {!Array.} Array of diff tuples. - * @private - */ -diff_match_patch.prototype.diff_lineMode_ = function(text1, text2, deadline) { - // Scan the text on a line-by-line basis first. - var a = this.diff_linesToChars_(text1, text2); - text1 = a.chars1; - text2 = a.chars2; - var linearray = a.lineArray; - - var diffs = this.diff_main(text1, text2, false, deadline); - - // Convert the diff back to original text. - this.diff_charsToLines_(diffs, linearray); - // Eliminate freak matches (e.g. blank lines) - this.diff_cleanupSemantic(diffs); - - // Rediff any replacement blocks, this time character-by-character. - // Add a dummy entry at the end. - diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, '')); - var pointer = 0; - var count_delete = 0; - var count_insert = 0; - var text_delete = ''; - var text_insert = ''; - while (pointer < diffs.length) { - switch (diffs[pointer][0]) { - case DIFF_INSERT: - count_insert++; - text_insert += diffs[pointer][1]; - break; - case DIFF_DELETE: - count_delete++; - text_delete += diffs[pointer][1]; - break; - case DIFF_EQUAL: - // Upon reaching an equality, check for prior redundancies. - if (count_delete >= 1 && count_insert >= 1) { - // Delete the offending records and add the merged ones. - diffs.splice(pointer - count_delete - count_insert, - count_delete + count_insert); - pointer = pointer - count_delete - count_insert; - var subDiff = - this.diff_main(text_delete, text_insert, false, deadline); - for (var j = subDiff.length - 1; j >= 0; j--) { - diffs.splice(pointer, 0, subDiff[j]); - } - pointer = pointer + subDiff.length; - } - count_insert = 0; - count_delete = 0; - text_delete = ''; - text_insert = ''; - break; - } - pointer++; - } - diffs.pop(); // Remove the dummy entry at the end. - - return diffs; -}; - - -/** - * Find the 'middle snake' of a diff, split the problem in two - * and return the recursively constructed diff. - * See Myers 1986 paper: An O(ND) Difference Algorithm and Its Variations. - * @param {string} text1 Old string to be diffed. - * @param {string} text2 New string to be diffed. - * @param {number} deadline Time at which to bail if not yet complete. - * @return {!Array.} Array of diff tuples. - * @private - */ -diff_match_patch.prototype.diff_bisect_ = function(text1, text2, deadline) { - // Cache the text lengths to prevent multiple calls. - var text1_length = text1.length; - var text2_length = text2.length; - var max_d = Math.ceil((text1_length + text2_length) / 2); - var v_offset = max_d; - var v_length = 2 * max_d; - var v1 = new Array(v_length); - var v2 = new Array(v_length); - // Setting all elements to -1 is faster in Chrome & Firefox than mixing - // integers and undefined. - for (var x = 0; x < v_length; x++) { - v1[x] = -1; - v2[x] = -1; - } - v1[v_offset + 1] = 0; - v2[v_offset + 1] = 0; - var delta = text1_length - text2_length; - // If the total number of characters is odd, then the front path will collide - // with the reverse path. - var front = (delta % 2 != 0); - // Offsets for start and end of k loop. - // Prevents mapping of space beyond the grid. - var k1start = 0; - var k1end = 0; - var k2start = 0; - var k2end = 0; - for (var d = 0; d < max_d; d++) { - // Bail out if deadline is reached. - if ((new Date()).getTime() > deadline) { - break; - } - - // Walk the front path one step. - for (var k1 = -d + k1start; k1 <= d - k1end; k1 += 2) { - var k1_offset = v_offset + k1; - var x1; - if (k1 == -d || (k1 != d && v1[k1_offset - 1] < v1[k1_offset + 1])) { - x1 = v1[k1_offset + 1]; - } else { - x1 = v1[k1_offset - 1] + 1; - } - var y1 = x1 - k1; - while (x1 < text1_length && y1 < text2_length && - text1.charAt(x1) == text2.charAt(y1)) { - x1++; - y1++; - } - v1[k1_offset] = x1; - if (x1 > text1_length) { - // Ran off the right of the graph. - k1end += 2; - } else if (y1 > text2_length) { - // Ran off the bottom of the graph. - k1start += 2; - } else if (front) { - var k2_offset = v_offset + delta - k1; - if (k2_offset >= 0 && k2_offset < v_length && v2[k2_offset] != -1) { - // Mirror x2 onto top-left coordinate system. - var x2 = text1_length - v2[k2_offset]; - if (x1 >= x2) { - // Overlap detected. - return this.diff_bisectSplit_(text1, text2, x1, y1, deadline); - } - } - } - } - - // Walk the reverse path one step. - for (var k2 = -d + k2start; k2 <= d - k2end; k2 += 2) { - var k2_offset = v_offset + k2; - var x2; - if (k2 == -d || (k2 != d && v2[k2_offset - 1] < v2[k2_offset + 1])) { - x2 = v2[k2_offset + 1]; - } else { - x2 = v2[k2_offset - 1] + 1; - } - var y2 = x2 - k2; - while (x2 < text1_length && y2 < text2_length && - text1.charAt(text1_length - x2 - 1) == - text2.charAt(text2_length - y2 - 1)) { - x2++; - y2++; - } - v2[k2_offset] = x2; - if (x2 > text1_length) { - // Ran off the left of the graph. - k2end += 2; - } else if (y2 > text2_length) { - // Ran off the top of the graph. - k2start += 2; - } else if (!front) { - var k1_offset = v_offset + delta - k2; - if (k1_offset >= 0 && k1_offset < v_length && v1[k1_offset] != -1) { - var x1 = v1[k1_offset]; - var y1 = v_offset + x1 - k1_offset; - // Mirror x2 onto top-left coordinate system. - x2 = text1_length - x2; - if (x1 >= x2) { - // Overlap detected. - return this.diff_bisectSplit_(text1, text2, x1, y1, deadline); - } - } - } - } - } - // Diff took too long and hit the deadline or - // number of diffs equals number of characters, no commonality at all. - return [new diff_match_patch.Diff(DIFF_DELETE, text1), - new diff_match_patch.Diff(DIFF_INSERT, text2)]; -}; - - -/** - * Given the location of the 'middle snake', split the diff in two parts - * and recurse. - * @param {string} text1 Old string to be diffed. - * @param {string} text2 New string to be diffed. - * @param {number} x Index of split point in text1. - * @param {number} y Index of split point in text2. - * @param {number} deadline Time at which to bail if not yet complete. - * @return {!Array.} Array of diff tuples. - * @private - */ -diff_match_patch.prototype.diff_bisectSplit_ = function(text1, text2, x, y, - deadline) { - var text1a = text1.substring(0, x); - var text2a = text2.substring(0, y); - var text1b = text1.substring(x); - var text2b = text2.substring(y); - - // Compute both diffs serially. - var diffs = this.diff_main(text1a, text2a, false, deadline); - var diffsb = this.diff_main(text1b, text2b, false, deadline); - - return diffs.concat(diffsb); -}; - - -/** - * Split two texts into an array of strings. Reduce the texts to a string of - * hashes where each Unicode character represents one line. - * @param {string} text1 First string. - * @param {string} text2 Second string. - * @return {{chars1: string, chars2: string, lineArray: !Array.}} - * An object containing the encoded text1, the encoded text2 and - * the array of unique strings. - * The zeroth element of the array of unique strings is intentionally blank. - * @private - */ -diff_match_patch.prototype.diff_linesToChars_ = function(text1, text2) { - var lineArray = []; // e.g. lineArray[4] == 'Hello\n' - var lineHash = {}; // e.g. lineHash['Hello\n'] == 4 - - // '\x00' is a valid character, but various debuggers don't like it. - // So we'll insert a junk entry to avoid generating a null character. - lineArray[0] = ''; - - /** - * Split a text into an array of strings. Reduce the texts to a string of - * hashes where each Unicode character represents one line. - * Modifies linearray and linehash through being a closure. - * @param {string} text String to encode. - * @return {string} Encoded string. - * @private - */ - function diff_linesToCharsMunge_(text) { - var chars = ''; - // Walk the text, pulling out a substring for each line. - // text.split('\n') would would temporarily double our memory footprint. - // Modifying text would create many large strings to garbage collect. - var lineStart = 0; - var lineEnd = -1; - // Keeping our own length variable is faster than looking it up. - var lineArrayLength = lineArray.length; - while (lineEnd < text.length - 1) { - lineEnd = text.indexOf('\n', lineStart); - if (lineEnd == -1) { - lineEnd = text.length - 1; - } - var line = text.substring(lineStart, lineEnd + 1); - - if (lineHash.hasOwnProperty ? lineHash.hasOwnProperty(line) : - (lineHash[line] !== undefined)) { - chars += String.fromCharCode(lineHash[line]); - } else { - if (lineArrayLength == maxLines) { - // Bail out at 65535 because - // String.fromCharCode(65536) == String.fromCharCode(0) - line = text.substring(lineStart); - lineEnd = text.length; - } - chars += String.fromCharCode(lineArrayLength); - lineHash[line] = lineArrayLength; - lineArray[lineArrayLength++] = line; - } - lineStart = lineEnd + 1; - } - return chars; - } - // Allocate 2/3rds of the space for text1, the rest for text2. - var maxLines = 40000; - var chars1 = diff_linesToCharsMunge_(text1); - maxLines = 65535; - var chars2 = diff_linesToCharsMunge_(text2); - return {chars1: chars1, chars2: chars2, lineArray: lineArray}; -}; - - -/** - * Rehydrate the text in a diff from a string of line hashes to real lines of - * text. - * @param {!Array.} diffs Array of diff tuples. - * @param {!Array.} lineArray Array of unique strings. - * @private - */ -diff_match_patch.prototype.diff_charsToLines_ = function(diffs, lineArray) { - for (var i = 0; i < diffs.length; i++) { - var chars = diffs[i][1]; - var text = []; - for (var j = 0; j < chars.length; j++) { - text[j] = lineArray[chars.charCodeAt(j)]; - } - diffs[i][1] = text.join(''); - } -}; - - -/** - * Determine the common prefix of two strings. - * @param {string} text1 First string. - * @param {string} text2 Second string. - * @return {number} The number of characters common to the start of each - * string. - */ -diff_match_patch.prototype.diff_commonPrefix = function(text1, text2) { - // Quick check for common null cases. - if (!text1 || !text2 || text1.charAt(0) != text2.charAt(0)) { - return 0; - } - // Binary search. - // Performance analysis: https://neil.fraser.name/news/2007/10/09/ - var pointermin = 0; - var pointermax = Math.min(text1.length, text2.length); - var pointermid = pointermax; - var pointerstart = 0; - while (pointermin < pointermid) { - if (text1.substring(pointerstart, pointermid) == - text2.substring(pointerstart, pointermid)) { - pointermin = pointermid; - pointerstart = pointermin; - } else { - pointermax = pointermid; - } - pointermid = Math.floor((pointermax - pointermin) / 2 + pointermin); - } - return pointermid; -}; - - -/** - * Determine the common suffix of two strings. - * @param {string} text1 First string. - * @param {string} text2 Second string. - * @return {number} The number of characters common to the end of each string. - */ -diff_match_patch.prototype.diff_commonSuffix = function(text1, text2) { - // Quick check for common null cases. - if (!text1 || !text2 || - text1.charAt(text1.length - 1) != text2.charAt(text2.length - 1)) { - return 0; - } - // Binary search. - // Performance analysis: https://neil.fraser.name/news/2007/10/09/ - var pointermin = 0; - var pointermax = Math.min(text1.length, text2.length); - var pointermid = pointermax; - var pointerend = 0; - while (pointermin < pointermid) { - if (text1.substring(text1.length - pointermid, text1.length - pointerend) == - text2.substring(text2.length - pointermid, text2.length - pointerend)) { - pointermin = pointermid; - pointerend = pointermin; - } else { - pointermax = pointermid; - } - pointermid = Math.floor((pointermax - pointermin) / 2 + pointermin); - } - return pointermid; -}; - - -/** - * Determine if the suffix of one string is the prefix of another. - * @param {string} text1 First string. - * @param {string} text2 Second string. - * @return {number} The number of characters common to the end of the first - * string and the start of the second string. - * @private - */ -diff_match_patch.prototype.diff_commonOverlap_ = function(text1, text2) { - // Cache the text lengths to prevent multiple calls. - var text1_length = text1.length; - var text2_length = text2.length; - // Eliminate the null case. - if (text1_length == 0 || text2_length == 0) { - return 0; - } - // Truncate the longer string. - if (text1_length > text2_length) { - text1 = text1.substring(text1_length - text2_length); - } else if (text1_length < text2_length) { - text2 = text2.substring(0, text1_length); - } - var text_length = Math.min(text1_length, text2_length); - // Quick check for the worst case. - if (text1 == text2) { - return text_length; - } - - // Start by looking for a single character match - // and increase length until no match is found. - // Performance analysis: https://neil.fraser.name/news/2010/11/04/ - var best = 0; - var length = 1; - while (true) { - var pattern = text1.substring(text_length - length); - var found = text2.indexOf(pattern); - if (found == -1) { - return best; - } - length += found; - if (found == 0 || text1.substring(text_length - length) == - text2.substring(0, length)) { - best = length; - length++; - } - } -}; - - -/** - * Do the two texts share a substring which is at least half the length of the - * longer text? - * This speedup can produce non-minimal diffs. - * @param {string} text1 First string. - * @param {string} text2 Second string. - * @return {Array.} Five element Array, containing the prefix of - * text1, the suffix of text1, the prefix of text2, the suffix of - * text2 and the common middle. Or null if there was no match. - * @private - */ -diff_match_patch.prototype.diff_halfMatch_ = function(text1, text2) { - if (this.Diff_Timeout <= 0) { - // Don't risk returning a non-optimal diff if we have unlimited time. - return null; - } - var longtext = text1.length > text2.length ? text1 : text2; - var shorttext = text1.length > text2.length ? text2 : text1; - if (longtext.length < 4 || shorttext.length * 2 < longtext.length) { - return null; // Pointless. - } - var dmp = this; // 'this' becomes 'window' in a closure. - - /** - * Does a substring of shorttext exist within longtext such that the substring - * is at least half the length of longtext? - * Closure, but does not reference any external variables. - * @param {string} longtext Longer string. - * @param {string} shorttext Shorter string. - * @param {number} i Start index of quarter length substring within longtext. - * @return {Array.} Five element Array, containing the prefix of - * longtext, the suffix of longtext, the prefix of shorttext, the suffix - * of shorttext and the common middle. Or null if there was no match. - * @private - */ - function diff_halfMatchI_(longtext, shorttext, i) { - // Start with a 1/4 length substring at position i as a seed. - var seed = longtext.substring(i, i + Math.floor(longtext.length / 4)); - var j = -1; - var best_common = ''; - var best_longtext_a, best_longtext_b, best_shorttext_a, best_shorttext_b; - while ((j = shorttext.indexOf(seed, j + 1)) != -1) { - var prefixLength = dmp.diff_commonPrefix(longtext.substring(i), - shorttext.substring(j)); - var suffixLength = dmp.diff_commonSuffix(longtext.substring(0, i), - shorttext.substring(0, j)); - if (best_common.length < suffixLength + prefixLength) { - best_common = shorttext.substring(j - suffixLength, j) + - shorttext.substring(j, j + prefixLength); - best_longtext_a = longtext.substring(0, i - suffixLength); - best_longtext_b = longtext.substring(i + prefixLength); - best_shorttext_a = shorttext.substring(0, j - suffixLength); - best_shorttext_b = shorttext.substring(j + prefixLength); - } - } - if (best_common.length * 2 >= longtext.length) { - return [best_longtext_a, best_longtext_b, - best_shorttext_a, best_shorttext_b, best_common]; - } else { - return null; - } - } - - // First check if the second quarter is the seed for a half-match. - var hm1 = diff_halfMatchI_(longtext, shorttext, - Math.ceil(longtext.length / 4)); - // Check again based on the third quarter. - var hm2 = diff_halfMatchI_(longtext, shorttext, - Math.ceil(longtext.length / 2)); - var hm; - if (!hm1 && !hm2) { - return null; - } else if (!hm2) { - hm = hm1; - } else if (!hm1) { - hm = hm2; - } else { - // Both matched. Select the longest. - hm = hm1[4].length > hm2[4].length ? hm1 : hm2; - } - - // A half-match was found, sort out the return data. - var text1_a, text1_b, text2_a, text2_b; - if (text1.length > text2.length) { - text1_a = hm[0]; - text1_b = hm[1]; - text2_a = hm[2]; - text2_b = hm[3]; - } else { - text2_a = hm[0]; - text2_b = hm[1]; - text1_a = hm[2]; - text1_b = hm[3]; - } - var mid_common = hm[4]; - return [text1_a, text1_b, text2_a, text2_b, mid_common]; -}; - - -/** - * Reduce the number of edits by eliminating semantically trivial equalities. - * @param {!Array.} diffs Array of diff tuples. - */ -diff_match_patch.prototype.diff_cleanupSemantic = function(diffs) { - var changes = false; - var equalities = []; // Stack of indices where equalities are found. - var equalitiesLength = 0; // Keeping our own length var is faster in JS. - /** @type {?string} */ - var lastEquality = null; - // Always equal to diffs[equalities[equalitiesLength - 1]][1] - var pointer = 0; // Index of current position. - // Number of characters that changed prior to the equality. - var length_insertions1 = 0; - var length_deletions1 = 0; - // Number of characters that changed after the equality. - var length_insertions2 = 0; - var length_deletions2 = 0; - while (pointer < diffs.length) { - if (diffs[pointer][0] == DIFF_EQUAL) { // Equality found. - equalities[equalitiesLength++] = pointer; - length_insertions1 = length_insertions2; - length_deletions1 = length_deletions2; - length_insertions2 = 0; - length_deletions2 = 0; - lastEquality = diffs[pointer][1]; - } else { // An insertion or deletion. - if (diffs[pointer][0] == DIFF_INSERT) { - length_insertions2 += diffs[pointer][1].length; - } else { - length_deletions2 += diffs[pointer][1].length; - } - // Eliminate an equality that is smaller or equal to the edits on both - // sides of it. - if (lastEquality && (lastEquality.length <= - Math.max(length_insertions1, length_deletions1)) && - (lastEquality.length <= Math.max(length_insertions2, - length_deletions2))) { - // Duplicate record. - diffs.splice(equalities[equalitiesLength - 1], 0, - new diff_match_patch.Diff(DIFF_DELETE, lastEquality)); - // Change second copy to insert. - diffs[equalities[equalitiesLength - 1] + 1][0] = DIFF_INSERT; - // Throw away the equality we just deleted. - equalitiesLength--; - // Throw away the previous equality (it needs to be reevaluated). - equalitiesLength--; - pointer = equalitiesLength > 0 ? equalities[equalitiesLength - 1] : -1; - length_insertions1 = 0; // Reset the counters. - length_deletions1 = 0; - length_insertions2 = 0; - length_deletions2 = 0; - lastEquality = null; - changes = true; - } - } - pointer++; - } - - // Normalize the diff. - if (changes) { - this.diff_cleanupMerge(diffs); - } - this.diff_cleanupSemanticLossless(diffs); - - // Find any overlaps between deletions and insertions. - // e.g: abcxxxxxxdef - // -> abcxxxdef - // e.g: xxxabcdefxxx - // -> defxxxabc - // Only extract an overlap if it is as big as the edit ahead or behind it. - pointer = 1; - while (pointer < diffs.length) { - if (diffs[pointer - 1][0] == DIFF_DELETE && - diffs[pointer][0] == DIFF_INSERT) { - var deletion = diffs[pointer - 1][1]; - var insertion = diffs[pointer][1]; - var overlap_length1 = this.diff_commonOverlap_(deletion, insertion); - var overlap_length2 = this.diff_commonOverlap_(insertion, deletion); - if (overlap_length1 >= overlap_length2) { - if (overlap_length1 >= deletion.length / 2 || - overlap_length1 >= insertion.length / 2) { - // Overlap found. Insert an equality and trim the surrounding edits. - diffs.splice(pointer, 0, new diff_match_patch.Diff(DIFF_EQUAL, - insertion.substring(0, overlap_length1))); - diffs[pointer - 1][1] = - deletion.substring(0, deletion.length - overlap_length1); - diffs[pointer + 1][1] = insertion.substring(overlap_length1); - pointer++; - } - } else { - if (overlap_length2 >= deletion.length / 2 || - overlap_length2 >= insertion.length / 2) { - // Reverse overlap found. - // Insert an equality and swap and trim the surrounding edits. - diffs.splice(pointer, 0, new diff_match_patch.Diff(DIFF_EQUAL, - deletion.substring(0, overlap_length2))); - diffs[pointer - 1][0] = DIFF_INSERT; - diffs[pointer - 1][1] = - insertion.substring(0, insertion.length - overlap_length2); - diffs[pointer + 1][0] = DIFF_DELETE; - diffs[pointer + 1][1] = - deletion.substring(overlap_length2); - pointer++; - } - } - pointer++; - } - pointer++; - } -}; - - -/** - * Look for single edits surrounded on both sides by equalities - * which can be shifted sideways to align the edit to a word boundary. - * e.g: The cat came. -> The cat came. - * @param {!Array.} diffs Array of diff tuples. - */ -diff_match_patch.prototype.diff_cleanupSemanticLossless = function(diffs) { - /** - * Given two strings, compute a score representing whether the internal - * boundary falls on logical boundaries. - * Scores range from 6 (best) to 0 (worst). - * Closure, but does not reference any external variables. - * @param {string} one First string. - * @param {string} two Second string. - * @return {number} The score. - * @private - */ - function diff_cleanupSemanticScore_(one, two) { - if (!one || !two) { - // Edges are the best. - return 6; - } - - // Each port of this function behaves slightly differently due to - // subtle differences in each language's definition of things like - // 'whitespace'. Since this function's purpose is largely cosmetic, - // the choice has been made to use each language's native features - // rather than force total conformity. - var char1 = one.charAt(one.length - 1); - var char2 = two.charAt(0); - var nonAlphaNumeric1 = char1.match(diff_match_patch.nonAlphaNumericRegex_); - var nonAlphaNumeric2 = char2.match(diff_match_patch.nonAlphaNumericRegex_); - var whitespace1 = nonAlphaNumeric1 && - char1.match(diff_match_patch.whitespaceRegex_); - var whitespace2 = nonAlphaNumeric2 && - char2.match(diff_match_patch.whitespaceRegex_); - var lineBreak1 = whitespace1 && - char1.match(diff_match_patch.linebreakRegex_); - var lineBreak2 = whitespace2 && - char2.match(diff_match_patch.linebreakRegex_); - var blankLine1 = lineBreak1 && - one.match(diff_match_patch.blanklineEndRegex_); - var blankLine2 = lineBreak2 && - two.match(diff_match_patch.blanklineStartRegex_); - - if (blankLine1 || blankLine2) { - // Five points for blank lines. - return 5; - } else if (lineBreak1 || lineBreak2) { - // Four points for line breaks. - return 4; - } else if (nonAlphaNumeric1 && !whitespace1 && whitespace2) { - // Three points for end of sentences. - return 3; - } else if (whitespace1 || whitespace2) { - // Two points for whitespace. - return 2; - } else if (nonAlphaNumeric1 || nonAlphaNumeric2) { - // One point for non-alphanumeric. - return 1; - } - return 0; - } - - var pointer = 1; - // Intentionally ignore the first and last element (don't need checking). - while (pointer < diffs.length - 1) { - if (diffs[pointer - 1][0] == DIFF_EQUAL && - diffs[pointer + 1][0] == DIFF_EQUAL) { - // This is a single edit surrounded by equalities. - var equality1 = diffs[pointer - 1][1]; - var edit = diffs[pointer][1]; - var equality2 = diffs[pointer + 1][1]; - - // First, shift the edit as far left as possible. - var commonOffset = this.diff_commonSuffix(equality1, edit); - if (commonOffset) { - var commonString = edit.substring(edit.length - commonOffset); - equality1 = equality1.substring(0, equality1.length - commonOffset); - edit = commonString + edit.substring(0, edit.length - commonOffset); - equality2 = commonString + equality2; - } - - // Second, step character by character right, looking for the best fit. - var bestEquality1 = equality1; - var bestEdit = edit; - var bestEquality2 = equality2; - var bestScore = diff_cleanupSemanticScore_(equality1, edit) + - diff_cleanupSemanticScore_(edit, equality2); - while (edit.charAt(0) === equality2.charAt(0)) { - equality1 += edit.charAt(0); - edit = edit.substring(1) + equality2.charAt(0); - equality2 = equality2.substring(1); - var score = diff_cleanupSemanticScore_(equality1, edit) + - diff_cleanupSemanticScore_(edit, equality2); - // The >= encourages trailing rather than leading whitespace on edits. - if (score >= bestScore) { - bestScore = score; - bestEquality1 = equality1; - bestEdit = edit; - bestEquality2 = equality2; - } - } - - if (diffs[pointer - 1][1] != bestEquality1) { - // We have an improvement, save it back to the diff. - if (bestEquality1) { - diffs[pointer - 1][1] = bestEquality1; - } else { - diffs.splice(pointer - 1, 1); - pointer--; - } - diffs[pointer][1] = bestEdit; - if (bestEquality2) { - diffs[pointer + 1][1] = bestEquality2; - } else { - diffs.splice(pointer + 1, 1); - pointer--; - } - } - } - pointer++; - } -}; - -// Define some regex patterns for matching boundaries. -diff_match_patch.nonAlphaNumericRegex_ = /[^a-zA-Z0-9]/; -diff_match_patch.whitespaceRegex_ = /\s/; -diff_match_patch.linebreakRegex_ = /[\r\n]/; -diff_match_patch.blanklineEndRegex_ = /\n\r?\n$/; -diff_match_patch.blanklineStartRegex_ = /^\r?\n\r?\n/; - -/** - * Reduce the number of edits by eliminating operationally trivial equalities. - * @param {!Array.} diffs Array of diff tuples. - */ -diff_match_patch.prototype.diff_cleanupEfficiency = function(diffs) { - var changes = false; - var equalities = []; // Stack of indices where equalities are found. - var equalitiesLength = 0; // Keeping our own length var is faster in JS. - /** @type {?string} */ - var lastEquality = null; - // Always equal to diffs[equalities[equalitiesLength - 1]][1] - var pointer = 0; // Index of current position. - // Is there an insertion operation before the last equality. - var pre_ins = false; - // Is there a deletion operation before the last equality. - var pre_del = false; - // Is there an insertion operation after the last equality. - var post_ins = false; - // Is there a deletion operation after the last equality. - var post_del = false; - while (pointer < diffs.length) { - if (diffs[pointer][0] == DIFF_EQUAL) { // Equality found. - if (diffs[pointer][1].length < this.Diff_EditCost && - (post_ins || post_del)) { - // Candidate found. - equalities[equalitiesLength++] = pointer; - pre_ins = post_ins; - pre_del = post_del; - lastEquality = diffs[pointer][1]; - } else { - // Not a candidate, and can never become one. - equalitiesLength = 0; - lastEquality = null; - } - post_ins = post_del = false; - } else { // An insertion or deletion. - if (diffs[pointer][0] == DIFF_DELETE) { - post_del = true; - } else { - post_ins = true; - } - /* - * Five types to be split: - * ABXYCD - * AXCD - * ABXC - * AXCD - * ABXC - */ - if (lastEquality && ((pre_ins && pre_del && post_ins && post_del) || - ((lastEquality.length < this.Diff_EditCost / 2) && - (pre_ins + pre_del + post_ins + post_del) == 3))) { - // Duplicate record. - diffs.splice(equalities[equalitiesLength - 1], 0, - new diff_match_patch.Diff(DIFF_DELETE, lastEquality)); - // Change second copy to insert. - diffs[equalities[equalitiesLength - 1] + 1][0] = DIFF_INSERT; - equalitiesLength--; // Throw away the equality we just deleted; - lastEquality = null; - if (pre_ins && pre_del) { - // No changes made which could affect previous entry, keep going. - post_ins = post_del = true; - equalitiesLength = 0; - } else { - equalitiesLength--; // Throw away the previous equality. - pointer = equalitiesLength > 0 ? - equalities[equalitiesLength - 1] : -1; - post_ins = post_del = false; - } - changes = true; - } - } - pointer++; - } - - if (changes) { - this.diff_cleanupMerge(diffs); - } -}; - - -/** - * Reorder and merge like edit sections. Merge equalities. - * Any edit section can move as long as it doesn't cross an equality. - * @param {!Array.} diffs Array of diff tuples. - */ -diff_match_patch.prototype.diff_cleanupMerge = function(diffs) { - // Add a dummy entry at the end. - diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, '')); - var pointer = 0; - var count_delete = 0; - var count_insert = 0; - var text_delete = ''; - var text_insert = ''; - var commonlength; - while (pointer < diffs.length) { - switch (diffs[pointer][0]) { - case DIFF_INSERT: - count_insert++; - text_insert += diffs[pointer][1]; - pointer++; - break; - case DIFF_DELETE: - count_delete++; - text_delete += diffs[pointer][1]; - pointer++; - break; - case DIFF_EQUAL: - // Upon reaching an equality, check for prior redundancies. - if (count_delete + count_insert > 1) { - if (count_delete !== 0 && count_insert !== 0) { - // Factor out any common prefixies. - commonlength = this.diff_commonPrefix(text_insert, text_delete); - if (commonlength !== 0) { - if ((pointer - count_delete - count_insert) > 0 && - diffs[pointer - count_delete - count_insert - 1][0] == - DIFF_EQUAL) { - diffs[pointer - count_delete - count_insert - 1][1] += - text_insert.substring(0, commonlength); - } else { - diffs.splice(0, 0, new diff_match_patch.Diff(DIFF_EQUAL, - text_insert.substring(0, commonlength))); - pointer++; - } - text_insert = text_insert.substring(commonlength); - text_delete = text_delete.substring(commonlength); - } - // Factor out any common suffixies. - commonlength = this.diff_commonSuffix(text_insert, text_delete); - if (commonlength !== 0) { - diffs[pointer][1] = text_insert.substring(text_insert.length - - commonlength) + diffs[pointer][1]; - text_insert = text_insert.substring(0, text_insert.length - - commonlength); - text_delete = text_delete.substring(0, text_delete.length - - commonlength); - } - } - // Delete the offending records and add the merged ones. - pointer -= count_delete + count_insert; - diffs.splice(pointer, count_delete + count_insert); - if (text_delete.length) { - diffs.splice(pointer, 0, - new diff_match_patch.Diff(DIFF_DELETE, text_delete)); - pointer++; - } - if (text_insert.length) { - diffs.splice(pointer, 0, - new diff_match_patch.Diff(DIFF_INSERT, text_insert)); - pointer++; - } - pointer++; - } else if (pointer !== 0 && diffs[pointer - 1][0] == DIFF_EQUAL) { - // Merge this equality with the previous one. - diffs[pointer - 1][1] += diffs[pointer][1]; - diffs.splice(pointer, 1); - } else { - pointer++; - } - count_insert = 0; - count_delete = 0; - text_delete = ''; - text_insert = ''; - break; - } - } - if (diffs[diffs.length - 1][1] === '') { - diffs.pop(); // Remove the dummy entry at the end. - } - - // Second pass: look for single edits surrounded on both sides by equalities - // which can be shifted sideways to eliminate an equality. - // e.g: ABAC -> ABAC - var changes = false; - pointer = 1; - // Intentionally ignore the first and last element (don't need checking). - while (pointer < diffs.length - 1) { - if (diffs[pointer - 1][0] == DIFF_EQUAL && - diffs[pointer + 1][0] == DIFF_EQUAL) { - // This is a single edit surrounded by equalities. - if (diffs[pointer][1].substring(diffs[pointer][1].length - - diffs[pointer - 1][1].length) == diffs[pointer - 1][1]) { - // Shift the edit over the previous equality. - diffs[pointer][1] = diffs[pointer - 1][1] + - diffs[pointer][1].substring(0, diffs[pointer][1].length - - diffs[pointer - 1][1].length); - diffs[pointer + 1][1] = diffs[pointer - 1][1] + diffs[pointer + 1][1]; - diffs.splice(pointer - 1, 1); - changes = true; - } else if (diffs[pointer][1].substring(0, diffs[pointer + 1][1].length) == - diffs[pointer + 1][1]) { - // Shift the edit over the next equality. - diffs[pointer - 1][1] += diffs[pointer + 1][1]; - diffs[pointer][1] = - diffs[pointer][1].substring(diffs[pointer + 1][1].length) + - diffs[pointer + 1][1]; - diffs.splice(pointer + 1, 1); - changes = true; - } - } - pointer++; - } - // If shifts were made, the diff needs reordering and another shift sweep. - if (changes) { - this.diff_cleanupMerge(diffs); - } -}; - - -/** - * loc is a location in text1, compute and return the equivalent location in - * text2. - * e.g. 'The cat' vs 'The big cat', 1->1, 5->8 - * @param {!Array.} diffs Array of diff tuples. - * @param {number} loc Location within text1. - * @return {number} Location within text2. - */ -diff_match_patch.prototype.diff_xIndex = function(diffs, loc) { - var chars1 = 0; - var chars2 = 0; - var last_chars1 = 0; - var last_chars2 = 0; - var x; - for (x = 0; x < diffs.length; x++) { - if (diffs[x][0] !== DIFF_INSERT) { // Equality or deletion. - chars1 += diffs[x][1].length; - } - if (diffs[x][0] !== DIFF_DELETE) { // Equality or insertion. - chars2 += diffs[x][1].length; - } - if (chars1 > loc) { // Overshot the location. - break; - } - last_chars1 = chars1; - last_chars2 = chars2; - } - // Was the location was deleted? - if (diffs.length != x && diffs[x][0] === DIFF_DELETE) { - return last_chars2; - } - // Add the remaining character length. - return last_chars2 + (loc - last_chars1); -}; - - -/** - * Convert a diff array into a pretty HTML report. - * @param {!Array.} diffs Array of diff tuples. - * @return {string} HTML representation. - */ -diff_match_patch.prototype.diff_prettyHtml = function(diffs) { - var html = []; - var pattern_amp = /&/g; - var pattern_lt = //g; - var pattern_para = /\n/g; - for (var x = 0; x < diffs.length; x++) { - var op = diffs[x][0]; // Operation (insert, delete, equal) - var data = diffs[x][1]; // Text of change. - var text = data.replace(pattern_amp, '&').replace(pattern_lt, '<') - .replace(pattern_gt, '>').replace(pattern_para, '¶
    '); - switch (op) { - case DIFF_INSERT: - html[x] = '' + text + ''; - break; - case DIFF_DELETE: - html[x] = '' + text + ''; - break; - case DIFF_EQUAL: - html[x] = '' + text + ''; - break; - } - } - return html.join(''); -}; - - -/** - * Compute and return the source text (all equalities and deletions). - * @param {!Array.} diffs Array of diff tuples. - * @return {string} Source text. - */ -diff_match_patch.prototype.diff_text1 = function(diffs) { - var text = []; - for (var x = 0; x < diffs.length; x++) { - if (diffs[x][0] !== DIFF_INSERT) { - text[x] = diffs[x][1]; - } - } - return text.join(''); -}; - - -/** - * Compute and return the destination text (all equalities and insertions). - * @param {!Array.} diffs Array of diff tuples. - * @return {string} Destination text. - */ -diff_match_patch.prototype.diff_text2 = function(diffs) { - var text = []; - for (var x = 0; x < diffs.length; x++) { - if (diffs[x][0] !== DIFF_DELETE) { - text[x] = diffs[x][1]; - } - } - return text.join(''); -}; - - -/** - * Compute the Levenshtein distance; the number of inserted, deleted or - * substituted characters. - * @param {!Array.} diffs Array of diff tuples. - * @return {number} Number of changes. - */ -diff_match_patch.prototype.diff_levenshtein = function(diffs) { - var levenshtein = 0; - var insertions = 0; - var deletions = 0; - for (var x = 0; x < diffs.length; x++) { - var op = diffs[x][0]; - var data = diffs[x][1]; - switch (op) { - case DIFF_INSERT: - insertions += data.length; - break; - case DIFF_DELETE: - deletions += data.length; - break; - case DIFF_EQUAL: - // A deletion and an insertion is one substitution. - levenshtein += Math.max(insertions, deletions); - insertions = 0; - deletions = 0; - break; - } - } - levenshtein += Math.max(insertions, deletions); - return levenshtein; -}; - - -/** - * Crush the diff into an encoded string which describes the operations - * required to transform text1 into text2. - * E.g. =3\t-2\t+ing -> Keep 3 chars, delete 2 chars, insert 'ing'. - * Operations are tab-separated. Inserted text is escaped using %xx notation. - * @param {!Array.} diffs Array of diff tuples. - * @return {string} Delta text. - */ -diff_match_patch.prototype.diff_toDelta = function(diffs) { - var text = []; - for (var x = 0; x < diffs.length; x++) { - switch (diffs[x][0]) { - case DIFF_INSERT: - text[x] = '+' + encodeURI(diffs[x][1]); - break; - case DIFF_DELETE: - text[x] = '-' + diffs[x][1].length; - break; - case DIFF_EQUAL: - text[x] = '=' + diffs[x][1].length; - break; - } - } - return text.join('\t').replace(/%20/g, ' '); -}; - - -/** - * Given the original text1, and an encoded string which describes the - * operations required to transform text1 into text2, compute the full diff. - * @param {string} text1 Source string for the diff. - * @param {string} delta Delta text. - * @return {!Array.} Array of diff tuples. - * @throws {!Error} If invalid input. - */ -diff_match_patch.prototype.diff_fromDelta = function(text1, delta) { - var diffs = []; - var diffsLength = 0; // Keeping our own length var is faster in JS. - var pointer = 0; // Cursor in text1 - var tokens = delta.split(/\t/g); - for (var x = 0; x < tokens.length; x++) { - // Each token begins with a one character parameter which specifies the - // operation of this token (delete, insert, equality). - var param = tokens[x].substring(1); - switch (tokens[x].charAt(0)) { - case '+': - try { - diffs[diffsLength++] = - new diff_match_patch.Diff(DIFF_INSERT, decodeURI(param)); - } catch (ex) { - // Malformed URI sequence. - throw new Error('Illegal escape in diff_fromDelta: ' + param); - } - break; - case '-': - // Fall through. - case '=': - var n = parseInt(param, 10); - if (isNaN(n) || n < 0) { - throw new Error('Invalid number in diff_fromDelta: ' + param); - } - var text = text1.substring(pointer, pointer += n); - if (tokens[x].charAt(0) == '=') { - diffs[diffsLength++] = new diff_match_patch.Diff(DIFF_EQUAL, text); - } else { - diffs[diffsLength++] = new diff_match_patch.Diff(DIFF_DELETE, text); - } - break; - default: - // Blank tokens are ok (from a trailing \t). - // Anything else is an error. - if (tokens[x]) { - throw new Error('Invalid diff operation in diff_fromDelta: ' + - tokens[x]); - } - } - } - if (pointer != text1.length) { - throw new Error('Delta length (' + pointer + - ') does not equal source text length (' + text1.length + ').'); - } - return diffs; -}; - - -// MATCH FUNCTIONS - - -/** - * Locate the best instance of 'pattern' in 'text' near 'loc'. - * @param {string} text The text to search. - * @param {string} pattern The pattern to search for. - * @param {number} loc The location to search around. - * @return {number} Best match index or -1. - */ -diff_match_patch.prototype.match_main = function(text, pattern, loc) { - // Check for null inputs. - if (text == null || pattern == null || loc == null) { - throw new Error('Null input. (match_main)'); - } - - loc = Math.max(0, Math.min(loc, text.length)); - if (text == pattern) { - // Shortcut (potentially not guaranteed by the algorithm) - return 0; - } else if (!text.length) { - // Nothing to match. - return -1; - } else if (text.substring(loc, loc + pattern.length) == pattern) { - // Perfect match at the perfect spot! (Includes case of null pattern) - return loc; - } else { - // Do a fuzzy compare. - return this.match_bitap_(text, pattern, loc); - } -}; - - -/** - * Locate the best instance of 'pattern' in 'text' near 'loc' using the - * Bitap algorithm. - * @param {string} text The text to search. - * @param {string} pattern The pattern to search for. - * @param {number} loc The location to search around. - * @return {number} Best match index or -1. - * @private - */ -diff_match_patch.prototype.match_bitap_ = function(text, pattern, loc) { - if (pattern.length > this.Match_MaxBits) { - throw new Error('Pattern too long for this browser.'); - } - - // Initialise the alphabet. - var s = this.match_alphabet_(pattern); - - var dmp = this; // 'this' becomes 'window' in a closure. - - /** - * Compute and return the score for a match with e errors and x location. - * Accesses loc and pattern through being a closure. - * @param {number} e Number of errors in match. - * @param {number} x Location of match. - * @return {number} Overall score for match (0.0 = good, 1.0 = bad). - * @private - */ - function match_bitapScore_(e, x) { - var accuracy = e / pattern.length; - var proximity = Math.abs(loc - x); - if (!dmp.Match_Distance) { - // Dodge divide by zero error. - return proximity ? 1.0 : accuracy; - } - return accuracy + (proximity / dmp.Match_Distance); - } - - // Highest score beyond which we give up. - var score_threshold = this.Match_Threshold; - // Is there a nearby exact match? (speedup) - var best_loc = text.indexOf(pattern, loc); - if (best_loc != -1) { - score_threshold = Math.min(match_bitapScore_(0, best_loc), score_threshold); - // What about in the other direction? (speedup) - best_loc = text.lastIndexOf(pattern, loc + pattern.length); - if (best_loc != -1) { - score_threshold = - Math.min(match_bitapScore_(0, best_loc), score_threshold); - } - } - - // Initialise the bit arrays. - var matchmask = 1 << (pattern.length - 1); - best_loc = -1; - - var bin_min, bin_mid; - var bin_max = pattern.length + text.length; - var last_rd; - for (var d = 0; d < pattern.length; d++) { - // Scan for the best match; each iteration allows for one more error. - // Run a binary search to determine how far from 'loc' we can stray at this - // error level. - bin_min = 0; - bin_mid = bin_max; - while (bin_min < bin_mid) { - if (match_bitapScore_(d, loc + bin_mid) <= score_threshold) { - bin_min = bin_mid; - } else { - bin_max = bin_mid; - } - bin_mid = Math.floor((bin_max - bin_min) / 2 + bin_min); - } - // Use the result from this iteration as the maximum for the next. - bin_max = bin_mid; - var start = Math.max(1, loc - bin_mid + 1); - var finish = Math.min(loc + bin_mid, text.length) + pattern.length; - - var rd = Array(finish + 2); - rd[finish + 1] = (1 << d) - 1; - for (var j = finish; j >= start; j--) { - // The alphabet (s) is a sparse hash, so the following line generates - // warnings. - var charMatch = s[text.charAt(j - 1)]; - if (d === 0) { // First pass: exact match. - rd[j] = ((rd[j + 1] << 1) | 1) & charMatch; - } else { // Subsequent passes: fuzzy match. - rd[j] = (((rd[j + 1] << 1) | 1) & charMatch) | - (((last_rd[j + 1] | last_rd[j]) << 1) | 1) | - last_rd[j + 1]; - } - if (rd[j] & matchmask) { - var score = match_bitapScore_(d, j - 1); - // This match will almost certainly be better than any existing match. - // But check anyway. - if (score <= score_threshold) { - // Told you so. - score_threshold = score; - best_loc = j - 1; - if (best_loc > loc) { - // When passing loc, don't exceed our current distance from loc. - start = Math.max(1, 2 * loc - best_loc); - } else { - // Already passed loc, downhill from here on in. - break; - } - } - } - } - // No hope for a (better) match at greater error levels. - if (match_bitapScore_(d + 1, loc) > score_threshold) { - break; - } - last_rd = rd; - } - return best_loc; -}; - - -/** - * Initialise the alphabet for the Bitap algorithm. - * @param {string} pattern The text to encode. - * @return {!Object} Hash of character locations. - * @private - */ -diff_match_patch.prototype.match_alphabet_ = function(pattern) { - var s = {}; - for (var i = 0; i < pattern.length; i++) { - s[pattern.charAt(i)] = 0; - } - for (var i = 0; i < pattern.length; i++) { - s[pattern.charAt(i)] |= 1 << (pattern.length - i - 1); - } - return s; -}; - - -// PATCH FUNCTIONS - - -/** - * Increase the context until it is unique, - * but don't let the pattern expand beyond Match_MaxBits. - * @param {!diff_match_patch.patch_obj} patch The patch to grow. - * @param {string} text Source text. - * @private - */ -diff_match_patch.prototype.patch_addContext_ = function(patch, text) { - if (text.length == 0) { - return; - } - if (patch.start2 === null) { - throw Error('patch not initialized'); - } - var pattern = text.substring(patch.start2, patch.start2 + patch.length1); - var padding = 0; - - // Look for the first and last matches of pattern in text. If two different - // matches are found, increase the pattern length. - while (text.indexOf(pattern) != text.lastIndexOf(pattern) && - pattern.length < this.Match_MaxBits - this.Patch_Margin - - this.Patch_Margin) { - padding += this.Patch_Margin; - pattern = text.substring(patch.start2 - padding, - patch.start2 + patch.length1 + padding); - } - // Add one chunk for good luck. - padding += this.Patch_Margin; - - // Add the prefix. - var prefix = text.substring(patch.start2 - padding, patch.start2); - if (prefix) { - patch.diffs.unshift(new diff_match_patch.Diff(DIFF_EQUAL, prefix)); - } - // Add the suffix. - var suffix = text.substring(patch.start2 + patch.length1, - patch.start2 + patch.length1 + padding); - if (suffix) { - patch.diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, suffix)); - } - - // Roll back the start points. - patch.start1 -= prefix.length; - patch.start2 -= prefix.length; - // Extend the lengths. - patch.length1 += prefix.length + suffix.length; - patch.length2 += prefix.length + suffix.length; -}; - - -/** - * Compute a list of patches to turn text1 into text2. - * Use diffs if provided, otherwise compute it ourselves. - * There are four ways to call this function, depending on what data is - * available to the caller: - * Method 1: - * a = text1, b = text2 - * Method 2: - * a = diffs - * Method 3 (optimal): - * a = text1, b = diffs - * Method 4 (deprecated, use method 3): - * a = text1, b = text2, c = diffs - * - * @param {string|!Array.} a text1 (methods 1,3,4) or - * Array of diff tuples for text1 to text2 (method 2). - * @param {string|!Array.=} opt_b text2 (methods 1,4) or - * Array of diff tuples for text1 to text2 (method 3) or undefined (method 2). - * @param {string|!Array.=} opt_c Array of diff tuples - * for text1 to text2 (method 4) or undefined (methods 1,2,3). - * @return {!Array.} Array of Patch objects. - */ -diff_match_patch.prototype.patch_make = function(a, opt_b, opt_c) { - var text1, diffs; - if (typeof a == 'string' && typeof opt_b == 'string' && - typeof opt_c == 'undefined') { - // Method 1: text1, text2 - // Compute diffs from text1 and text2. - text1 = /** @type {string} */(a); - diffs = this.diff_main(text1, /** @type {string} */(opt_b), true); - if (diffs.length > 2) { - this.diff_cleanupSemantic(diffs); - this.diff_cleanupEfficiency(diffs); - } - } else if (a && typeof a == 'object' && typeof opt_b == 'undefined' && - typeof opt_c == 'undefined') { - // Method 2: diffs - // Compute text1 from diffs. - diffs = /** @type {!Array.} */(a); - text1 = this.diff_text1(diffs); - } else if (typeof a == 'string' && opt_b && typeof opt_b == 'object' && - typeof opt_c == 'undefined') { - // Method 3: text1, diffs - text1 = /** @type {string} */(a); - diffs = /** @type {!Array.} */(opt_b); - } else if (typeof a == 'string' && typeof opt_b == 'string' && - opt_c && typeof opt_c == 'object') { - // Method 4: text1, text2, diffs - // text2 is not used. - text1 = /** @type {string} */(a); - diffs = /** @type {!Array.} */(opt_c); - } else { - throw new Error('Unknown call format to patch_make.'); - } - - if (diffs.length === 0) { - return []; // Get rid of the null case. - } - var patches = []; - var patch = new diff_match_patch.patch_obj(); - var patchDiffLength = 0; // Keeping our own length var is faster in JS. - var char_count1 = 0; // Number of characters into the text1 string. - var char_count2 = 0; // Number of characters into the text2 string. - // Start with text1 (prepatch_text) and apply the diffs until we arrive at - // text2 (postpatch_text). We recreate the patches one by one to determine - // context info. - var prepatch_text = text1; - var postpatch_text = text1; - for (var x = 0; x < diffs.length; x++) { - var diff_type = diffs[x][0]; - var diff_text = diffs[x][1]; - - if (!patchDiffLength && diff_type !== DIFF_EQUAL) { - // A new patch starts here. - patch.start1 = char_count1; - patch.start2 = char_count2; - } - - switch (diff_type) { - case DIFF_INSERT: - patch.diffs[patchDiffLength++] = diffs[x]; - patch.length2 += diff_text.length; - postpatch_text = postpatch_text.substring(0, char_count2) + diff_text + - postpatch_text.substring(char_count2); - break; - case DIFF_DELETE: - patch.length1 += diff_text.length; - patch.diffs[patchDiffLength++] = diffs[x]; - postpatch_text = postpatch_text.substring(0, char_count2) + - postpatch_text.substring(char_count2 + - diff_text.length); - break; - case DIFF_EQUAL: - if (diff_text.length <= 2 * this.Patch_Margin && - patchDiffLength && diffs.length != x + 1) { - // Small equality inside a patch. - patch.diffs[patchDiffLength++] = diffs[x]; - patch.length1 += diff_text.length; - patch.length2 += diff_text.length; - } else if (diff_text.length >= 2 * this.Patch_Margin) { - // Time for a new patch. - if (patchDiffLength) { - this.patch_addContext_(patch, prepatch_text); - patches.push(patch); - patch = new diff_match_patch.patch_obj(); - patchDiffLength = 0; - // Unlike Unidiff, our patch lists have a rolling context. - // https://github.com/google/diff-match-patch/wiki/Unidiff - // Update prepatch text & pos to reflect the application of the - // just completed patch. - prepatch_text = postpatch_text; - char_count1 = char_count2; - } - } - break; - } - - // Update the current character count. - if (diff_type !== DIFF_INSERT) { - char_count1 += diff_text.length; - } - if (diff_type !== DIFF_DELETE) { - char_count2 += diff_text.length; - } - } - // Pick up the leftover patch if not empty. - if (patchDiffLength) { - this.patch_addContext_(patch, prepatch_text); - patches.push(patch); - } - - return patches; -}; - - -/** - * Given an array of patches, return another array that is identical. - * @param {!Array.} patches Array of Patch objects. - * @return {!Array.} Array of Patch objects. - */ -diff_match_patch.prototype.patch_deepCopy = function(patches) { - // Making deep copies is hard in JavaScript. - var patchesCopy = []; - for (var x = 0; x < patches.length; x++) { - var patch = patches[x]; - var patchCopy = new diff_match_patch.patch_obj(); - patchCopy.diffs = []; - for (var y = 0; y < patch.diffs.length; y++) { - patchCopy.diffs[y] = - new diff_match_patch.Diff(patch.diffs[y][0], patch.diffs[y][1]); - } - patchCopy.start1 = patch.start1; - patchCopy.start2 = patch.start2; - patchCopy.length1 = patch.length1; - patchCopy.length2 = patch.length2; - patchesCopy[x] = patchCopy; - } - return patchesCopy; -}; - - -/** - * Merge a set of patches onto the text. Return a patched text, as well - * as a list of true/false values indicating which patches were applied. - * @param {!Array.} patches Array of Patch objects. - * @param {string} text Old text. - * @return {!Array.>} Two element Array, containing the - * new text and an array of boolean values. - */ -diff_match_patch.prototype.patch_apply = function(patches, text) { - if (patches.length == 0) { - return [text, []]; - } - - // Deep copy the patches so that no changes are made to originals. - patches = this.patch_deepCopy(patches); - - var nullPadding = this.patch_addPadding(patches); - text = nullPadding + text + nullPadding; - - this.patch_splitMax(patches); - // delta keeps track of the offset between the expected and actual location - // of the previous patch. If there are patches expected at positions 10 and - // 20, but the first patch was found at 12, delta is 2 and the second patch - // has an effective expected position of 22. - var delta = 0; - var results = []; - for (var x = 0; x < patches.length; x++) { - var expected_loc = patches[x].start2 + delta; - var text1 = this.diff_text1(patches[x].diffs); - var start_loc; - var end_loc = -1; - if (text1.length > this.Match_MaxBits) { - // patch_splitMax will only provide an oversized pattern in the case of - // a monster delete. - start_loc = this.match_main(text, text1.substring(0, this.Match_MaxBits), - expected_loc); - if (start_loc != -1) { - end_loc = this.match_main(text, - text1.substring(text1.length - this.Match_MaxBits), - expected_loc + text1.length - this.Match_MaxBits); - if (end_loc == -1 || start_loc >= end_loc) { - // Can't find valid trailing context. Drop this patch. - start_loc = -1; - } - } - } else { - start_loc = this.match_main(text, text1, expected_loc); - } - if (start_loc == -1) { - // No match found. :( - results[x] = false; - // Subtract the delta for this failed patch from subsequent patches. - delta -= patches[x].length2 - patches[x].length1; - } else { - // Found a match. :) - results[x] = true; - delta = start_loc - expected_loc; - var text2; - if (end_loc == -1) { - text2 = text.substring(start_loc, start_loc + text1.length); - } else { - text2 = text.substring(start_loc, end_loc + this.Match_MaxBits); - } - if (text1 == text2) { - // Perfect match, just shove the replacement text in. - text = text.substring(0, start_loc) + - this.diff_text2(patches[x].diffs) + - text.substring(start_loc + text1.length); - } else { - // Imperfect match. Run a diff to get a framework of equivalent - // indices. - var diffs = this.diff_main(text1, text2, false); - if (text1.length > this.Match_MaxBits && - this.diff_levenshtein(diffs) / text1.length > - this.Patch_DeleteThreshold) { - // The end points match, but the content is unacceptably bad. - results[x] = false; - } else { - this.diff_cleanupSemanticLossless(diffs); - var index1 = 0; - var index2; - for (var y = 0; y < patches[x].diffs.length; y++) { - var mod = patches[x].diffs[y]; - if (mod[0] !== DIFF_EQUAL) { - index2 = this.diff_xIndex(diffs, index1); - } - if (mod[0] === DIFF_INSERT) { // Insertion - text = text.substring(0, start_loc + index2) + mod[1] + - text.substring(start_loc + index2); - } else if (mod[0] === DIFF_DELETE) { // Deletion - text = text.substring(0, start_loc + index2) + - text.substring(start_loc + this.diff_xIndex(diffs, - index1 + mod[1].length)); - } - if (mod[0] !== DIFF_DELETE) { - index1 += mod[1].length; - } - } - } - } - } - } - // Strip the padding off. - text = text.substring(nullPadding.length, text.length - nullPadding.length); - return [text, results]; -}; - - -/** - * Add some padding on text start and end so that edges can match something. - * Intended to be called only from within patch_apply. - * @param {!Array.} patches Array of Patch objects. - * @return {string} The padding string added to each side. - */ -diff_match_patch.prototype.patch_addPadding = function(patches) { - var paddingLength = this.Patch_Margin; - var nullPadding = ''; - for (var x = 1; x <= paddingLength; x++) { - nullPadding += String.fromCharCode(x); - } - - // Bump all the patches forward. - for (var x = 0; x < patches.length; x++) { - patches[x].start1 += paddingLength; - patches[x].start2 += paddingLength; - } - - // Add some padding on start of first diff. - var patch = patches[0]; - var diffs = patch.diffs; - if (diffs.length == 0 || diffs[0][0] != DIFF_EQUAL) { - // Add nullPadding equality. - diffs.unshift(new diff_match_patch.Diff(DIFF_EQUAL, nullPadding)); - patch.start1 -= paddingLength; // Should be 0. - patch.start2 -= paddingLength; // Should be 0. - patch.length1 += paddingLength; - patch.length2 += paddingLength; - } else if (paddingLength > diffs[0][1].length) { - // Grow first equality. - var extraLength = paddingLength - diffs[0][1].length; - diffs[0][1] = nullPadding.substring(diffs[0][1].length) + diffs[0][1]; - patch.start1 -= extraLength; - patch.start2 -= extraLength; - patch.length1 += extraLength; - patch.length2 += extraLength; - } - - // Add some padding on end of last diff. - patch = patches[patches.length - 1]; - diffs = patch.diffs; - if (diffs.length == 0 || diffs[diffs.length - 1][0] != DIFF_EQUAL) { - // Add nullPadding equality. - diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, nullPadding)); - patch.length1 += paddingLength; - patch.length2 += paddingLength; - } else if (paddingLength > diffs[diffs.length - 1][1].length) { - // Grow last equality. - var extraLength = paddingLength - diffs[diffs.length - 1][1].length; - diffs[diffs.length - 1][1] += nullPadding.substring(0, extraLength); - patch.length1 += extraLength; - patch.length2 += extraLength; - } - - return nullPadding; -}; - - -/** - * Look through the patches and break up any which are longer than the maximum - * limit of the match algorithm. - * Intended to be called only from within patch_apply. - * @param {!Array.} patches Array of Patch objects. - */ -diff_match_patch.prototype.patch_splitMax = function(patches) { - var patch_size = this.Match_MaxBits; - for (var x = 0; x < patches.length; x++) { - if (patches[x].length1 <= patch_size) { - continue; - } - var bigpatch = patches[x]; - // Remove the big old patch. - patches.splice(x--, 1); - var start1 = bigpatch.start1; - var start2 = bigpatch.start2; - var precontext = ''; - while (bigpatch.diffs.length !== 0) { - // Create one of several smaller patches. - var patch = new diff_match_patch.patch_obj(); - var empty = true; - patch.start1 = start1 - precontext.length; - patch.start2 = start2 - precontext.length; - if (precontext !== '') { - patch.length1 = patch.length2 = precontext.length; - patch.diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, precontext)); - } - while (bigpatch.diffs.length !== 0 && - patch.length1 < patch_size - this.Patch_Margin) { - var diff_type = bigpatch.diffs[0][0]; - var diff_text = bigpatch.diffs[0][1]; - if (diff_type === DIFF_INSERT) { - // Insertions are harmless. - patch.length2 += diff_text.length; - start2 += diff_text.length; - patch.diffs.push(bigpatch.diffs.shift()); - empty = false; - } else if (diff_type === DIFF_DELETE && patch.diffs.length == 1 && - patch.diffs[0][0] == DIFF_EQUAL && - diff_text.length > 2 * patch_size) { - // This is a large deletion. Let it pass in one chunk. - patch.length1 += diff_text.length; - start1 += diff_text.length; - empty = false; - patch.diffs.push(new diff_match_patch.Diff(diff_type, diff_text)); - bigpatch.diffs.shift(); - } else { - // Deletion or equality. Only take as much as we can stomach. - diff_text = diff_text.substring(0, - patch_size - patch.length1 - this.Patch_Margin); - patch.length1 += diff_text.length; - start1 += diff_text.length; - if (diff_type === DIFF_EQUAL) { - patch.length2 += diff_text.length; - start2 += diff_text.length; - } else { - empty = false; - } - patch.diffs.push(new diff_match_patch.Diff(diff_type, diff_text)); - if (diff_text == bigpatch.diffs[0][1]) { - bigpatch.diffs.shift(); - } else { - bigpatch.diffs[0][1] = - bigpatch.diffs[0][1].substring(diff_text.length); - } - } - } - // Compute the head context for the next patch. - precontext = this.diff_text2(patch.diffs); - precontext = - precontext.substring(precontext.length - this.Patch_Margin); - // Append the end context for this patch. - var postcontext = this.diff_text1(bigpatch.diffs) - .substring(0, this.Patch_Margin); - if (postcontext !== '') { - patch.length1 += postcontext.length; - patch.length2 += postcontext.length; - if (patch.diffs.length !== 0 && - patch.diffs[patch.diffs.length - 1][0] === DIFF_EQUAL) { - patch.diffs[patch.diffs.length - 1][1] += postcontext; - } else { - patch.diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, postcontext)); - } - } - if (!empty) { - patches.splice(++x, 0, patch); - } - } - } -}; - - -/** - * Take a list of patches and return a textual representation. - * @param {!Array.} patches Array of Patch objects. - * @return {string} Text representation of patches. - */ -diff_match_patch.prototype.patch_toText = function(patches) { - var text = []; - for (var x = 0; x < patches.length; x++) { - text[x] = patches[x]; - } - return text.join(''); -}; - - -/** - * Parse a textual representation of patches and return a list of Patch objects. - * @param {string} textline Text representation of patches. - * @return {!Array.} Array of Patch objects. - * @throws {!Error} If invalid input. - */ -diff_match_patch.prototype.patch_fromText = function(textline) { - var patches = []; - if (!textline) { - return patches; - } - var text = textline.split('\n'); - var textPointer = 0; - var patchHeader = /^@@ -(\d+),?(\d*) \+(\d+),?(\d*) @@$/; - while (textPointer < text.length) { - var m = text[textPointer].match(patchHeader); - if (!m) { - throw new Error('Invalid patch string: ' + text[textPointer]); - } - var patch = new diff_match_patch.patch_obj(); - patches.push(patch); - patch.start1 = parseInt(m[1], 10); - if (m[2] === '') { - patch.start1--; - patch.length1 = 1; - } else if (m[2] == '0') { - patch.length1 = 0; - } else { - patch.start1--; - patch.length1 = parseInt(m[2], 10); - } - - patch.start2 = parseInt(m[3], 10); - if (m[4] === '') { - patch.start2--; - patch.length2 = 1; - } else if (m[4] == '0') { - patch.length2 = 0; - } else { - patch.start2--; - patch.length2 = parseInt(m[4], 10); - } - textPointer++; - - while (textPointer < text.length) { - var sign = text[textPointer].charAt(0); - try { - var line = decodeURI(text[textPointer].substring(1)); - } catch (ex) { - // Malformed URI sequence. - throw new Error('Illegal escape in patch_fromText: ' + line); - } - if (sign == '-') { - // Deletion. - patch.diffs.push(new diff_match_patch.Diff(DIFF_DELETE, line)); - } else if (sign == '+') { - // Insertion. - patch.diffs.push(new diff_match_patch.Diff(DIFF_INSERT, line)); - } else if (sign == ' ') { - // Minor equality. - patch.diffs.push(new diff_match_patch.Diff(DIFF_EQUAL, line)); - } else if (sign == '@') { - // Start of next patch. - break; - } else if (sign === '') { - // Blank line? Whatever. - } else { - // WTF? - throw new Error('Invalid patch mode "' + sign + '" in: ' + line); - } - textPointer++; - } - } - return patches; -}; - - -/** - * Class representing one patch operation. - * @constructor - */ -diff_match_patch.patch_obj = function() { - /** @type {!Array.} */ - this.diffs = []; - /** @type {?number} */ - this.start1 = null; - /** @type {?number} */ - this.start2 = null; - /** @type {number} */ - this.length1 = 0; - /** @type {number} */ - this.length2 = 0; -}; - - -/** - * Emulate GNU diff's format. - * Header: @@ -382,8 +481,9 @@ - * Indices are printed as 1-based, not 0-based. - * @return {string} The GNU diff string. - */ -diff_match_patch.patch_obj.prototype.toString = function() { - var coords1, coords2; - if (this.length1 === 0) { - coords1 = this.start1 + ',0'; - } else if (this.length1 == 1) { - coords1 = this.start1 + 1; - } else { - coords1 = (this.start1 + 1) + ',' + this.length1; - } - if (this.length2 === 0) { - coords2 = this.start2 + ',0'; - } else if (this.length2 == 1) { - coords2 = this.start2 + 1; - } else { - coords2 = (this.start2 + 1) + ',' + this.length2; - } - var text = ['@@ -' + coords1 + ' +' + coords2 + ' @@\n']; - var op; - // Escape the body of the patch with %xx notation. - for (var x = 0; x < this.diffs.length; x++) { - switch (this.diffs[x][0]) { - case DIFF_INSERT: - op = '+'; - break; - case DIFF_DELETE: - op = '-'; - break; - case DIFF_EQUAL: - op = ' '; - break; - } - text[x + 1] = op + encodeURI(this.diffs[x][1]) + '\n'; - } - return text.join('').replace(/%20/g, ' '); -}; - -// CLOSURE:begin_strip -// Lines below here will not be included in the Closure-compatible library. - -// Export these global variables so that they survive Google's JS compiler. -// In a browser, 'this' will be 'window'. -// Users of node.js should 'require' the uncompressed version since Google's -// JS compiler may break the following exports for non-browser environments. -/** @suppress {globalThis} */ -this['diff_match_patch'] = diff_match_patch; -/** @suppress {globalThis} */ -this['DIFF_DELETE'] = DIFF_DELETE; -/** @suppress {globalThis} */ -this['DIFF_INSERT'] = DIFF_INSERT; -/** @suppress {globalThis} */ -this['DIFF_EQUAL'] = DIFF_EQUAL; diff --git a/resources/svg2img.sh b/resources/svg2img.sh deleted file mode 100755 index 1d1d412..0000000 --- a/resources/svg2img.sh +++ /dev/null @@ -1,94 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -svg_dir="$script_dir/svg" -out_dir="$script_dir/img" -sizes=(16 32 64) -themes=(light dark) - -get_theme_color() { - case "$1" in - light) printf '%s\n' '#000000' ;; - dark) printf '%s\n' '#ffffff' ;; - *) - printf 'Unknown theme: %s\n' "$1" >&2 - exit 1 - ;; - esac -} - -ensure_temp_svg() { - local input_svg="$1" - local color="$2" - local temp_svg="$3" - - python3 - "$input_svg" "$color" "$temp_svg" <<'PY' -import pathlib -import re -import sys - -input_path = pathlib.Path(sys.argv[1]) -color = sys.argv[2] -output_path = pathlib.Path(sys.argv[3]) -content = input_path.read_text(encoding="utf-8") -patched, count = re.subn(r"]*?)>", f'', content, count=1) -if count != 1: - raise SystemExit("Couldn't find tag to patch.") -output_path.write_text(patched, encoding="utf-8") -PY -} - -if [[ ! -d "$svg_dir" ]]; then - echo "SVG source directory not found: $svg_dir" >&2 - exit 1 -fi - -mkdir -p "$out_dir" - -if ! command -v inkscape >/dev/null 2>&1; then - echo "Inkscape CLI is not installed or not in PATH. Please install it from https://inkscape.org/" >&2 - exit 1 -fi - -if ! command -v python3 >/dev/null 2>&1; then - echo "python3 is required to patch the SVG color attribute." >&2 - exit 1 -fi - -shopt -s nullglob -svg_files=("$svg_dir"/*.svg) -shopt -u nullglob - -if [[ ${#svg_files[@]} -eq 0 ]]; then - echo "No SVG files found in $svg_dir" >&2 - exit 0 -fi - -temp_svg="$(mktemp "${TMPDIR:-/tmp}/sortana-svg2img.XXXXXX.svg")" -cleanup() { - rm -f "$temp_svg" -} -trap cleanup EXIT - -for svg_path in "${svg_files[@]}"; do - base_name="$(basename "${svg_path%.svg}")" - - for theme in "${themes[@]}"; do - color="$(get_theme_color "$theme")" - ensure_temp_svg "$svg_path" "$color" "$temp_svg" - - for size in "${sizes[@]}"; do - out_file="$out_dir/$base_name-$theme-$size.png" - echo "Exporting $out_file (color $color)..." - inkscape "$temp_svg" \ - --export-type=png \ - --export-filename="$out_file" \ - --export-width="$size" \ - --export-height="$size" \ - --actions=export-do - done - done -done - -echo "Done generating light/dark themed PNGs." diff --git a/tests/batching.test.mjs b/tests/batching.test.mjs deleted file mode 100644 index 000ebe3..0000000 --- a/tests/batching.test.mjs +++ /dev/null @@ -1,219 +0,0 @@ -import test from 'node:test'; -import assert from 'node:assert/strict'; -import vm from 'node:vm'; -import { readFile } from 'node:fs/promises'; -import { CONFIG_DEFAULTS, validateSettings } from '../modules/classificationConfig.js'; -import * as systemone from '../modules/backends/systemOne.js'; - -const data = {}; -let cacheWrites = 0; -globalThis.messenger = { storage: { local: { - async get(keys) { return Object.fromEntries((Array.isArray(keys) ? keys : [keys]).map(key => [key, data[key]])); }, - async set(values) { Object.assign(data, structuredClone(values)); if ('aiCache' in values) cacheWrites++; }, - async remove() {} -} }, messages: { async get(id) { return { headerMessageId: `mail-${id}` }; } } }; -const classifier = await import('../modules/AiClassifier.js'); -const transfer = await import('../options/dataTransfer.js'); -let requests = []; -async function setup(update = {}) { - await classifier.clearCache(); - classifier.setConfig({ ...CONFIG_DEFAULTS, apiType: 'systemone', ...update }); - requests = []; cacheWrites = 0; - globalThis.fetch = async (url, request) => { - const body = JSON.parse(request.body); - requests.push({ url, body, headers: request.headers }); - // Intentionally reverse response order and include an unsolicited answer. - return { ok: true, json: async () => ({ model: 'served', answers: { - unsolicited: { type: 'noul', noul: 1 }, - ...Object.fromEntries(Object.keys(body.questions).reverse().map(id => [id, { type: 'noul', noul: 0.75 }])) - } }) }; - }; - return classifier.getConfig(); -} -async function candidates(count, snapshot, criteria = []) { - return Promise.all(Array.from({ length: count }, async (_, i) => { - const criterion = criteria[i] ?? `criterion ${i}`; - return { id: `rule_${i}`, rule: { criterion, actions: [] }, cacheKey: await classifier.buildCacheKey(1, criterion, snapshot) }; - })); -} -async function collect(items, snapshot) { - const results = []; - for await (const value of classifier.classifyRules('email state', items, snapshot)) results.push(value); - return results; -} - -test('Process all, explicit batch sizes, partial batches, empty input and cache reuse', async () => { - for (const [settings, expected] of [ - [{}, [10]], [{ systemOneProcessAll: false, systemOneBatchSize: 8 }, [8, 2]], - [{ systemOneProcessAll: false, systemOneBatchSize: 1 }, Array(10).fill(1)] - ]) { - const snapshot = await setup(settings); - const items = await candidates(10, snapshot); - const results = await collect(items, snapshot); - assert.deepEqual(requests.map(r => Object.keys(r.body.questions).length), expected); - assert.equal(cacheWrites, expected.length); - assert.deepEqual(results.map(r => r.rule.criterion), items.map(r => r.rule.criterion)); - assert.ok(results.every(r => r.result.probability === 0.75)); - assert.ok(requests.every(r => r.body.state === 'email state' && !('messages' in r.body))); - await collect(items, snapshot); - assert.equal(requests.length, expected.length); - await collect([], snapshot); - assert.equal(requests.length, expected.length); - } -}); - -test('cached rules consume no capacity and duplicate criteria use independent thresholds', async () => { - const snapshot = await setup({ systemOneProcessAll: false, systemOneBatchSize: 2 }); - const items = await candidates(5, snapshot, ['cached', 'same', 'cached', 'other', 'same']); - await collect([items[0]], snapshot); - requests = []; cacheWrites = 0; - items[1].rule.decisionThreshold = 0.8; - items[4].rule.decisionThreshold = 0.7; - const results = await collect(items, snapshot); - assert.equal(requests.length, 1); - assert.deepEqual(Object.keys(requests[0].body.questions), ['rule_1', 'rule_3']); - assert.equal(results[1].result.matched, false); - assert.equal(results[4].result.matched, true); - assert.equal(cacheWrites, 1); - assert.equal(await classifier.buildCacheKey(1, 'same', { ...snapshot, systemOneProcessAll: true, systemOneBatchSize: 100 }), items[1].cacheKey); -}); - -test('answer identity determines probability, not answer order', () => { - const result = { answers: { rule_2: { type: 'noul', noul: 0 }, rule_1: { type: 'noul', noul: 1 } } }; - assert.deepEqual(systemone.parseBatchResponse(result, [{ id: 'rule_1' }, { id: 'rule_2' }]).map(r => r.probability), [1, 0]); -}); - -test('failed batches neither yield nor cache partial results and do not retry', async () => { - for (const failure of ['missing', 'invalid', 'http']) { - const snapshot = await setup(); - const items = await candidates(2, snapshot); - let calls = 0, yielded = 0; - globalThis.fetch = async () => { - calls++; - return { ok: failure !== 'http', status: 413, json: async () => ({ answers: { - rule_0: { type: 'noul', noul: 0.9 }, - ...(failure === 'invalid' ? { rule_1: { type: 'noul', noul: '0.9' } } : {}) - } }) }; - }; - await assert.rejects(async () => { - for await (const value of classifier.classifyRules('state', items, snapshot)) yielded++; - }); - assert.equal(yielded, 0); - assert.equal(calls, 1); - assert.equal(cacheWrites, 0); - assert.equal(await classifier.getCacheSize(), 0); - } -}); - -test('clearing or importing during a batch prevents stale cache writes', async () => { - for (const replace of [() => classifier.clearCache(), () => classifier.replaceCache({})]) { - const snapshot = await setup(); - const items = await candidates(2, snapshot); - const fetch = globalThis.fetch; - globalThis.fetch = async (...args) => { await replace(); return fetch(...args); }; - const results = await collect(items, snapshot); - assert.equal(results.length, 2); - assert.equal(requests.length, 1); - assert.equal(await classifier.getCacheSize(), 0); - } -}); - -test('Chat Completions remains lazy and sequential', async () => { - const snapshot = await setup({ apiType: 'chat-completions' }); - const items = await candidates(3, snapshot); - globalThis.fetch = async (url, request) => { - requests.push(JSON.parse(request.body)); - return { ok: true, json: async () => ({ choices: [{ message: { content: '{"match":true}' } }] }) }; - }; - for await (const value of classifier.classifyRules('state', items, snapshot)) break; - assert.equal(requests.length, 1); - assert.ok(Array.isArray(requests[0].messages)); -}); - -test('batch settings validate and survive import', async () => { - for (const value of [0, -1, 1.2, Infinity, '8', null]) assert.throws(() => validateSettings({ systemOneBatchSize: value })); - assert.throws(() => validateSettings({ systemOneProcessAll: 'true' })); - await transfer.importData({ text: async () => JSON.stringify({ systemOneProcessAll: false, systemOneBatchSize: 3 }) }, ['settings']); - assert.equal(data.systemOneProcessAll, false); - assert.equal(data.systemOneBatchSize, 3); - await assert.rejects(transfer.importData({ text: async () => '{"systemOneBatchSize":0}' }, ['settings'])); -}); - -// Exercise the action runner with the real lazy classifier and mocked mail APIs. -const source = await readFile(new URL('../background.js', import.meta.url), 'utf8'); -const functions = source.slice(source.indexOf('async function processMessage('), source.indexOf('async function clearCacheForMessages(')); -test('stop after match skips later actions and batches; all-mode retains later evidence', async () => { - for (const processAll of [true, false]) { - const snapshot = await setup({ systemOneProcessAll: processAll, systemOneBatchSize: 2 }); - const actions = [], errors = []; - const rules = Array.from({ length: 5 }, (_, i) => ({ criterion: `rule ${i}`, actions: [{ type: 'flag', flagged: true }], stopProcessing: i === 1 })); - const context = vm.createContext({ - structuredClone, Date, Error, aiRules: rules, AiClassifier: classifier, - queue: Promise.resolve(), queuedCount: 0, processing: false, currentStart: 0, - tokenReduction: false, showDebugTab: false, timingStats: {}, - updateActionIcon() {}, updateTimingStats() {}, showTransientIcon() {}, - buildEmailText() { return 'state'; }, ICONS: { circle: 'circle' }, - logger: { aiLog() {} }, recordError(...args) { errors.push(args); }, ERROR_NOTIFICATION_ID: 'error', - storage: messenger.storage, - messenger: { messages: { - async getFull() { return {}; }, async get() { return { tags: [], folder: { accountId: 'account' } }; }, - async update(id, value) { actions.push({ id, value }); } - }, identities: { async list() { return []; } } }, - browser: { runtime: { getURL: x => x }, notifications: { async create() {} } } - }); - vm.runInContext(functions, context); - await vm.runInContext('applyAiRules([1])', context); - assert.equal(errors.length, 0); - assert.equal(actions.length, 2); - assert.equal(requests.length, 1); - assert.equal(Object.keys(requests[0].body.questions).length, processAll ? 5 : 2); - assert.equal(await classifier.getCacheSize(), processAll ? 5 : 2); - } -}); - -test('batch controls default to all and retain numeric input across toggles and API switches', async () => { - const optionsSource = await readFile(new URL('../options/options.js', import.meta.url), 'utf8'); - const section = optionsSource.slice(optionsSource.indexOf(' const apiTypeInput ='), optionsSource.indexOf(' const endpointInput =')); - const fields = new Map(); - const field = id => { - if (!fields.has(id)) fields.set(id, { - value: '', checked: false, disabled: false, listeners: {}, - addEventListener(event, fn) { this.listeners[event] = fn; }, - classList: { toggle() {} }, closest() { return this; } - }); - return fields.get(id); - }; - const context = vm.createContext({ - defaults: { apiType: 'systemone' }, DEFAULT_AI_PARAMS: {}, migratedInputLimit() { return 3686; }, - updateEndpointPreview() {}, document: { getElementById: field, querySelectorAll() { return []; } } - }); - vm.runInContext(`${section}\nupdateApiControls();`, context); - const all = field('systemone-process-all'), size = field('systemone-batch-size'), api = field('api-type'); - assert.equal(all.checked, true); - assert.equal(size.value, 8); - assert.equal(size.disabled, true); - all.checked = false; all.listeners.change(); - assert.equal(size.disabled, false); - size.value = '3'; - all.checked = true; all.listeners.change(); - assert.equal(size.disabled, true); - all.checked = false; all.listeners.change(); - assert.equal(size.value, '3'); - api.value = 'chat-completions'; api.listeners.change(); - assert.equal(size.disabled, true); - api.value = 'systemone'; api.listeners.change(); - assert.equal(size.disabled, false); - assert.equal(size.value, '3'); -}); - -test('batch settings remain fixed while a per-email snapshot is running', async () => { - const snapshot = await setup({ systemOneProcessAll: false, systemOneBatchSize: 2 }); - const items = await candidates(5, snapshot); - const fetch = globalThis.fetch; - globalThis.fetch = async (...args) => { - classifier.setConfig({ systemOneProcessAll: true, systemOneBatchSize: 1 }); - return fetch(...args); - }; - await collect(items, snapshot); - assert.deepEqual(requests.map(r => Object.keys(r.body.questions).length), [2, 2, 1]); -}); diff --git a/tests/cacheRestore.test.mjs b/tests/cacheRestore.test.mjs deleted file mode 100644 index 91a8515..0000000 --- a/tests/cacheRestore.test.mjs +++ /dev/null @@ -1,86 +0,0 @@ -import test from 'node:test'; -import assert from 'node:assert/strict'; -import vm from 'node:vm'; -import { readFile } from 'node:fs/promises'; -import { CONFIG_DEFAULTS } from '../modules/classificationConfig.js'; - -const persisted = {}; -const listeners = []; -const storage = { - local: { - async get(keys) { - return Object.fromEntries((Array.isArray(keys) ? keys : [keys]) - .filter(key => key in persisted).map(key => [key, structuredClone(persisted[key])])); - }, - async set(values) { - const changes = {}; - for (const [key, value] of Object.entries(values)) { - changes[key] = { oldValue: persisted[key], newValue: structuredClone(value) }; - persisted[key] = structuredClone(value); - } - for (const listener of listeners) await listener(changes, 'local'); - }, - async remove(keys) { - for (const key of Array.isArray(keys) ? keys : [keys]) delete persisted[key]; - } - }, - onChanged: { addListener(listener) { listeners.push(listener); } } -}; -const messenger = { storage, messages: { async get(id) { - // Numeric Thunderbird IDs may change after reinstall; RFC Message-ID does not. - return { subject: 'Invoice', headerMessageId: 'persistent-message@example.com' }; -} } }; -globalThis.messenger = messenger; -const classifier = await import('../modules/AiClassifier.js'); -const transfer = await import('../options/dataTransfer.js'); -const source = await readFile(new URL('../background.js', import.meta.url), 'utf8'); -let onMessage; -const context = vm.createContext({ - storage, messenger, structuredClone, AiClassifier: classifier, aiRules: [], - logger: { aiLog() {} }, logGetTiming: false, - htmlToMarkdown: false, stripUrlParams: false, altTextImages: false, - collapseWhitespace: false, tokenReduction: false, showDebugTab: false, - browser: { runtime: { onMessage: { addListener(listener) { onMessage = listener; } } } } -}); -// Exercise the actual background storage and Details handlers, not a manual cache reload. -const normalizeStart = source.indexOf('function normalizeRules('); -vm.runInContext(source.slice(normalizeStart, source.indexOf('function iconPaths(', normalizeStart)), context); -const changesStart = source.indexOf('storage.onChanged.addListener('); -vm.runInContext(source.slice(changesStart, source.indexOf('\n\n if (browser.theme', changesStart)), context); -const messageStart = source.indexOf('browser.runtime.onMessage.addListener('); -vm.runInContext(source.slice(messageStart, source.indexOf('\n\n // Automatically classify', messageStart)), context); - -test('export/reinstall/import restores Details immediately with changed Thunderbird IDs', async () => { - const settings = { ...CONFIG_DEFAULTS, systemOneProcessAll: false, systemOneBatchSize: 3, apiType: 'systemone', endpoint: 'http://decision-server:8080', tokenReduction: true, inputCharacterLimit: 5000 }; - const rules = [{ criterion: 'invoice', decisionThreshold: 0.8, actions: [] }]; - await storage.local.set({ ...settings, aiRules: rules }); - globalThis.fetch = async () => ({ ok: true, json: async () => ({ answers: { match: { type: 'noul', noul: 0.9 } } }) }); - const key = await classifier.buildCacheKey(1, 'invoice'); - await classifier.classify('Invoice attached', 'invoice', { cacheKey: key, threshold: 0.8 }); - let exported; - const originalDocument = globalThis.document; - const createURL = URL.createObjectURL; - const revokeURL = URL.revokeObjectURL; - URL.createObjectURL = blob => { exported = blob; return 'blob:export'; }; - URL.revokeObjectURL = () => {}; - globalThis.document = { body: { appendChild() {} }, createElement() { return { click() {}, remove() {} }; } }; - try { await transfer.exportData(['settings', 'rules', 'cache']); } - finally { globalThis.document = originalDocument; URL.createObjectURL = createURL; URL.revokeObjectURL = revokeURL; } - await classifier.clearCache(); - for (const key of Object.keys(persisted)) delete persisted[key]; - classifier.setConfig(CONFIG_DEFAULTS); - context.aiRules = []; - assert.equal((await onMessage({ type: 'sortana:getDetails', id: 99 })).results.length, 0); - await transfer.importData(exported, ['settings', 'rules', 'cache']); - assert.equal((await onMessage({ type: 'sortana:getCacheSize' })).count, 1); - assert.equal(classifier.getConfig().systemOneProcessAll, false); - assert.equal(classifier.getConfig().systemOneBatchSize, 3); - const details = await onMessage({ type: 'sortana:getDetails', id: 99 }); - assert.equal(details.results.length, 1); - assert.equal(details.results[0].criterion, 'invoice'); - assert.equal(details.results[0].probability, 0.9); - assert.equal(details.results[0].threshold, 0.8); - assert.equal(details.results[0].matched, true); - globalThis.fetch = () => { throw new Error('Restored cache must avoid inference'); }; - assert.equal((await classifier.classify('Invoice attached', 'invoice', { cacheKey: await classifier.buildCacheKey(99, 'invoice') })).matched, true); -}); diff --git a/tests/classification.test.mjs b/tests/classification.test.mjs deleted file mode 100644 index daf6ea6..0000000 --- a/tests/classification.test.mjs +++ /dev/null @@ -1,167 +0,0 @@ -import test from 'node:test'; -import assert from 'node:assert/strict'; -import * as chat from '../modules/backends/chatCompletions.js'; -import * as decision from '../modules/backends/systemOne.js'; -import { CONFIG_DEFAULTS, migratedInputLimit, validateSettings } from '../modules/classificationConfig.js'; - -const data = { aiCache: { legacy: { matched: true, reason: 'old' } }, aiReasonCache: { legacy: 'old' } }; -globalThis.messenger = { storage: { local: { - async get(keys) { return Object.fromEntries((Array.isArray(keys) ? keys : [keys]).map(key => [key, data[key]])); }, - async set(values) { Object.assign(data, structuredClone(values)); }, - async remove(keys) { for (const key of Array.isArray(keys) ? keys : [keys]) delete data[key]; } -} }, messages: { async get(id) { return { headerMessageId: `message-${id}` }; } } }; -const classifier = await import('../modules/AiClassifier.js'); -const transfer = await import('../options/dataTransfer.js'); -const answer = probability => ({ model: 'served-model', answers: { match: { type: 'noul', noul: probability } } }); -let calls = []; -function serve(body, status = 200) { - globalThis.fetch = async (url, request) => { calls.push({ url, ...request }); return { ok: status === 200, status, json: async () => body }; }; -} - -test('adapters preserve chat prompts and isolate SystemOne payloads', () => { - const config = { ...CONFIG_DEFAULTS, model: 'chosen', customSystemPrompt: 'Custom guidance' }; - const payload = chat.buildRequest('email', 'invoice', config); - assert.match(payload.messages[0].content, /Custom guidance/); - assert.match(payload.messages[1].content, /Classification Criterion: invoice/); - assert.equal(payload.max_tokens, 4096); - assert.deepEqual(decision.buildRequest('email', 'invoice', config), { - state: 'email', model: 'chosen', questions: { match: { type: 'noul', instructions: 'Does this email satisfy the following criterion: invoice' } } - }); - assert.equal('model' in decision.buildRequest('email', 'invoice', CONFIG_DEFAULTS), false); - assert.equal('model' in chat.buildRequest('email', 'invoice', CONFIG_DEFAULTS), false); -}); - -test('parsers validate evidence including zero, one, and malformed answers', () => { - for (const probability of [0, 0.5, 1]) assert.equal(decision.parseResponse(answer(probability)).probability, probability); - for (const probability of [null, '0.5', -0.1, 1.1, Infinity, NaN]) assert.throws(() => decision.parseResponse(answer(probability))); - for (const raw of [null, {}, { answers: { other: { type: 'noul', noul: 0.5 } } }, { answers: { match: { type: 'choice', noul: 0.5 } } }]) assert.throws(() => decision.parseResponse(raw)); - assert.deepEqual(chat.parseResponse({ choices: [{ message: { content: 'text {"match":false} then {"matched":true,"reason":"brace } inside"}' } }] }), { matched: true, reason: 'brace } inside', probability: null }); - for (const content of ['', '{broken}', '{"match":"true"}']) assert.throws(() => chat.parseResponse({ choices: [{ message: { content } }] })); - assert.throws(() => chat.parseResponse(null)); -}); - -test('URLs preserve proxy prefixes and normalize API suffixes', () => { - for (const suffix of ['', '/', '/v1', '/v1/', '/v1/models', '/v1/chat/completions/', '/v1/systemone']) { - assert.equal(classifier.buildEndpointUrl(`http://localhost:8080/proxy${suffix}`, 'systemone'), 'http://localhost:8080/proxy/v1/systemone'); - assert.equal(classifier.buildModelsUrl(`http://localhost:8080/proxy${suffix}`), 'http://localhost:8080/proxy/v1/models'); - } - assert.equal(classifier.buildEndpointUrl('example.com'), 'https://example.com/v1/chat/completions'); - assert.equal(classifier.buildEndpointUrl(''), ''); -}); - -test('settings validation and independent character-limit migration', () => { - assert.equal(migratedInputLimit({}), 3686); - assert.equal(migratedInputLimit({ aiParams: { max_tokens: 1000 } }), 900); - assert.equal(migratedInputLimit({ inputCharacterLimit: 500, aiParams: { max_tokens: 1000 } }), 500); - validateSettings({ decisionThreshold: 0, aiRules: [{ decisionThreshold: 1 }] }); - for (const value of [-1, 2, null, '0.5']) assert.throws(() => validateSettings({ aiRules: [{ decisionThreshold: value }] })); - for (const value of [0, 1.2, NaN]) assert.throws(() => validateSettings({ inputCharacterLimit: value })); -}); - -test('cache migration, inference reuse, fingerprints, clearing and import', async () => { - await classifier.init(); - assert.equal(await classifier.getCacheSize(), 0); - assert.equal(data.aiReasonCache, undefined); - assert.deepEqual(data.aiCache, {}); - classifier.setConfig({ ...CONFIG_DEFAULTS, apiType: 'systemone', endpoint: 'http://localhost:8080', apiKey: 'secret', openaiOrganization: 'org', openaiProject: 'project' }); - const snapshot = classifier.getConfig(); - const key = await classifier.buildCacheKey(1, 'invoice', snapshot); - serve(answer(0.75)); calls = []; - const first = await classifier.classify('email', 'invoice', { snapshot, cacheKey: key, threshold: 0.75 }); - assert.equal(first.matched, true); - assert.equal(first.model, 'served-model'); - assert.deepEqual(calls[0].headers, { 'Content-Type': 'application/json', Authorization: 'Bearer secret' }); - const second = await classifier.classify('email', 'invoice', { snapshot, cacheKey: key, threshold: 0.8 }); - assert.equal(second.matched, false); - assert.equal(second.probability, 0.75); - assert.equal(calls.length, 1); - classifier.replaceCache(data.aiCache); - assert.equal(classifier.getCachedDetails(key, 0.75).matched, true); - assert.equal(await classifier.buildCacheKey(1, 'invoice', { ...snapshot, decisionThreshold: 0.9, apiKey: 'new secret' }), key); - for (const change of [{ apiType: 'chat-completions' }, { endpoint: 'http://other' }, { model: 'other' }, { tokenReduction: true }, { inputCharacterLimit: 500 }]) { - assert.notEqual(await classifier.buildCacheKey(1, 'invoice', { ...snapshot, ...change }), key); - } - const chatSnapshot = { ...snapshot, apiType: 'chat-completions' }; - const chatKey = await classifier.buildCacheKey(1, 'invoice', chatSnapshot); - assert.notEqual(await classifier.buildCacheKey(1, 'invoice', { ...chatSnapshot, customSystemPrompt: 'other' }), chatKey); - assert.notEqual(await classifier.buildCacheKey(1, 'invoice', { ...chatSnapshot, aiParams: { ...snapshot.aiParams, temperature: 1 } }), chatKey); - serve({ choices: [{ message: { content: '{"match":false,"reason":"not invoice"}' } }] }); - await classifier.classify('email', 'invoice', { cacheKey: chatKey, snapshot: chatSnapshot }); - assert.equal(calls.at(-1).headers['OpenAI-Organization'], 'org'); - assert.equal(await classifier.getCacheSize(), 2); - const exported = structuredClone(data.aiCache); - await classifier.clearCacheForMessage(1); - assert.equal(await classifier.getCacheSize(), 0); - await transfer.importData({ text: async () => JSON.stringify({ aiCache: { ...exported, legacy: true } }) }, ['cache']); - classifier.replaceCache(data.aiCache); // background storage listener consumes imported replacement - assert.equal(await classifier.getCacheSize(), 2); - await assert.rejects(transfer.importData({ text: async () => JSON.stringify({ decisionThreshold: 2 }) }, ['settings'])); - await assert.rejects(transfer.importData({ text: async () => JSON.stringify({ aiRules: [{ decisionThreshold: -1 }] }) }, ['rules'])); - await classifier.clearCache(); -}); - -test('failures remain uncached and snapshots survive configuration changes', async () => { - classifier.setConfig({ ...CONFIG_DEFAULTS, apiType: 'systemone' }); - const snapshot = classifier.getConfig(); - const key = await classifier.buildCacheKey(2, 'invoice', snapshot); - for (const raw of [null, answer('0.9'), {}]) { - serve(raw); - await assert.rejects(classifier.classify('email', 'invoice', { cacheKey: key, snapshot })); - assert.equal(classifier.getCachedDetails(key), null); - } - serve({}, 503); - await assert.rejects(classifier.classify('email', 'invoice', { cacheKey: key, snapshot }), /503/); - globalThis.fetch = async () => { throw new Error('network'); }; - await assert.rejects(classifier.classify('email', 'invoice', { cacheKey: key, snapshot }), /network/); - globalThis.fetch = async () => ({ ok: true, json: async () => { throw new SyntaxError('bad JSON'); } }); - await assert.rejects(classifier.classify('email', 'invoice', { cacheKey: key, snapshot }), /bad JSON/); - classifier.setConfig({ apiType: 'chat-completions', endpoint: 'http://changed' }); - serve(answer(1)); calls = []; - const result = await classifier.classify('email', 'invoice', { cacheKey: key, snapshot }); - assert.equal(result.backend, 'systemone'); - assert.equal(calls[0].url, 'http://127.0.0.1:5000/v1/systemone'); - assert.equal('Authorization' in calls[0].headers, false); - await classifier.clearCache(); -}); - -test('clearing or replacing cache during inference prevents stale repopulation', async () => { - classifier.setConfig({ ...CONFIG_DEFAULTS, apiType: 'systemone' }); - const snapshot = classifier.getConfig(); - const key = await classifier.buildCacheKey(3, 'invoice', snapshot); - for (const replace of [() => classifier.clearCache(), () => classifier.replaceCache({})]) { - let release, started; - const ready = new Promise(resolve => { started = resolve; }); - globalThis.fetch = async () => { - started(); - await new Promise(resolve => { release = resolve; }); - return { ok: true, json: async () => answer(0.9) }; - }; - const pending = classifier.classify('email', 'invoice', { cacheKey: key, snapshot }); - await ready; - await replace(); - release(); - assert.equal((await pending).matched, true); - assert.equal(classifier.getCachedDetails(key), null); - } -}); - -test('settings and rule imports retain thresholds and reject invalid caches', async () => { - const settings = { apiType: 'systemone', decisionThreshold: 0.75, inputCharacterLimit: 5000, tokenReduction: true }; - const rules = [{ criterion: 'invoice', decisionThreshold: 0, actions: [{ type: 'flag', flagged: true }] }, { criterion: 'urgent', actions: [] }]; - await transfer.importData({ text: async () => JSON.stringify({ ...settings, aiRules: rules }) }, ['settings', 'rules']); - for (const [key, value] of Object.entries(settings)) assert.equal(data[key], value); - assert.deepEqual(data.aiRules, rules); - const key = await classifier.buildCacheKey(4, 'invoice'); - assert.equal(classifier.validCacheEntry(key, { version: 2, backend: 'systemone', probability: '0.8', reason: null, messageHash: key.split(':')[1], model: '' }), false); -}); - -test('SystemOne 404 reports endpoint, server message, and compatibility guidance', async () => { - classifier.setConfig({ ...CONFIG_DEFAULTS, apiType: 'systemone', endpoint: 'http://seinei.wageshouse:5003' }); - serve({ error: { message: 'File Not Found' } }, 404); - await assert.rejects(classifier.classify('synthetic email', 'invoice'), error => { - assert.match(error.message, /HTTP 404 at http:\/\/seinei\.wageshouse:5003\/v1\/systemone/); - assert.match(error.message, /Server response: File Not Found/); - assert.match(error.message, /running server build supports/); - return true; - }); -}); diff --git a/tests/ruleExecution.test.mjs b/tests/ruleExecution.test.mjs deleted file mode 100644 index 327a14d..0000000 --- a/tests/ruleExecution.test.mjs +++ /dev/null @@ -1,83 +0,0 @@ -import test from 'node:test'; -import assert from 'node:assert/strict'; -import vm from 'node:vm'; -import { readFile } from 'node:fs/promises'; - -// Run the actual background rule/queue functions with Thunderbird services mocked. -const source = await readFile(new URL('../background.js', import.meta.url), 'utf8'); -const functions = source.slice(source.indexOf('async function processMessage('), source.indexOf('async function clearCacheForMessages(')); -function runner({ fail = false, changeSettings = false } = {}) { - const actions = [], evaluated = [], errors = []; - const rules = [ - { criterion: 'first', decisionThreshold: 0.8, actions: [{ type: 'flag', flagged: true }], stopProcessing: true }, - { criterion: 'second', actions: [{ type: 'read', read: true }] } - ]; - let currentConfig = { apiType: 'systemone', inputCharacterLimit: 5, decisionThreshold: 0.5 }; - const context = vm.createContext({ - structuredClone, Date, Error, - aiRules: rules, queue: Promise.resolve(), queuedCount: 0, processing: false, - currentStart: 0, tokenReduction: true, showDebugTab: false, timingStats: {}, - updateActionIcon() {}, updateTimingStats() {}, showTransientIcon() {}, - buildEmailText() { return 'email contents'; }, ICONS: { circle: 'circle' }, - logger: { aiLog() {} }, recordError(...args) { errors.push(args); }, - ERROR_NOTIFICATION_ID: 'error', - storage: { local: { async set() {} } }, - messenger: { - messages: { - async getFull() { return {}; }, - async get() { - if (changeSettings) { - rules[0].decisionThreshold = 0.1; - currentConfig = { apiType: 'chat-completions', decisionThreshold: 0.1 }; - } - return { tags: [], folder: { accountId: 'account' } }; - }, - async update(id, action) { actions.push({ id, ...action }); } - }, identities: { async list() { return []; } } - }, - browser: { runtime: { getURL: x => x }, notifications: { async create() {} } }, - AiClassifier: { - getConfig() { return structuredClone(currentConfig); }, - async buildCacheKey(id, criterion) { return `${id}:${criterion}`; }, - async *classifyRules(text, candidates, snapshot) { - for (const { rule, cacheKey } of candidates) { - evaluated.push({ text, criterion: rule.criterion, cacheKey, snapshot, - threshold: rule.decisionThreshold ?? snapshot.decisionThreshold }); - if (fail && cacheKey.startsWith('1:')) throw new Error('inference failed'); - yield { rule, result: { matched: true } }; - } - } - } - }); - vm.runInContext(functions, context); - return { context, actions, evaluated, errors }; -} - -test('failure stops remaining rules for one email, next queued email still acts', async () => { - const { context, actions, evaluated, errors } = runner({ fail: true }); - await vm.runInContext('applyAiRules([1, 2])', context); - assert.deepEqual(evaluated.map(x => x.cacheKey), ['1:first', '2:first']); - assert.deepEqual(actions, [{ id: 2, flagged: true }]); - assert.equal(errors.length, 1); - assert.equal(context.processing, false); - assert.equal(context.queuedCount, 0); -}); - -test('settings and rules remain fixed during an email; reduction uses characters', async () => { - const { context, evaluated, actions } = runner({ changeSettings: true }); - await vm.runInContext('applyAiRules([1])', context); - assert.equal(evaluated[0].text, 'email'); - assert.equal(evaluated[0].threshold, 0.8); - assert.equal(evaluated[0].snapshot.apiType, 'systemone'); - assert.equal(evaluated.length, 1); // stop after first match - assert.equal(actions.length, 1); -}); - -test('inherited thresholds and eligibility preserve ordered rule processing', async () => { - const { context, evaluated, actions } = runner(); - context.aiRules[0].enabled = false; - await vm.runInContext('applyAiRules([1])', context); - assert.equal(evaluated[0].criterion, 'second'); - assert.equal(evaluated[0].threshold, 0.5); - assert.deepEqual(actions, [{ id: 1, read: true }]); -});