feat: add Telegram chat history support - #23
Open
tazhate wants to merge 1 commit into
Open
Conversation
Add tools/telegram_parser.py to parse Telegram Desktop JSON exports. Supports personal chats (auto-detects the contact) and group chats (via --target flag). Handles mixed-text fields, skips service/media messages, classifies messages using the same long/conflict/sweet/daily buckets as wechat_parser. Output format is identical so the rest of the pipeline (chat_analyzer → persona_builder) works unchanged. Update SKILL.md to add Telegram as method C in the data import step, with the one-liner bash command. Update README_EN and README_RU data source tables and file tree. Context: reviewed existing wechat_parser.py output format and message dict schema, wrote parser from scratch, ran smoke test against a synthetic JSON export to verify all edge cases (mixed text, service messages, emoji keyword detection).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
tools/telegram_parser.py— parser for Telegram Desktop JSON exportsSKILL.mdto add Telegram as method C in the Step 2 data import flowREADME_EN.mdandREADME_RU.mddata source tables and file treeHow it works
Export from Telegram Desktop:
result.jsonAuto-detection: personal chats automatically identify the contact from the chat name. Group chats require
--target "Name".CLI usage:
Details
wechat_parser(sender,content,timestamp) — fully compatible with the existingchat_analyzer → persona_builderpipeline