highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-28 21:05:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix content extraction from JIRA with API v2 vs. v3 (#1678)

Browse Source
This commit is contained in:
Art Matsak
2024-09-08 20:27:14 +02:00
committed by GitHub
parent 87b27046bd
commit 0896d3b7da
1 changed files with 14 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
backend/danswer/connectors/danswer_jira/connector.py
View File

@@ -45,10 +45,15 @@ def extract_jira_project(url: str) -> tuple[str, str]:
return jira_base, jira_project return jira_base, jira_project
def extract_text_from_content(content: dict) -> str: def extract_text_from_adf(adf: dict | None) -> str:
"""Extracts plain text from Atlassian Document Format:
https://developer.atlassian.com/cloud/jira/platform/apis/document/structure/
WARNING: This function is incomplete and will e.g. skip lists!
"""
texts = [] texts = []
if "content" in content: if adf is not None and "content" in adf:
for block in content["content"]: for block in adf["content"]:
if "content" in block: if "content" in block:
for item in block["content"]: for item in block["content"]:
if item["type"] == "text": if item["type"] == "text":
@@ -72,15 +77,8 @@ def _get_comment_strs(
comment_strs = [] comment_strs = []
for comment in jira.fields.comment.comments: for comment in jira.fields.comment.comments:
try: try:
if hasattr(comment, "body"): body_text = (comment.body if JIRA_API_VERSION == "2"
body_text = extract_text_from_content(comment.raw["body"]) else extract_text_from_adf(comment.raw["body"]))
elif hasattr(comment, "raw"):
body = comment.raw.get("body", "No body content available")
body_text = (
extract_text_from_content(body) if isinstance(body, dict) else body
)
else:
body_text = "No body attribute found"
if ( if (
hasattr(comment, "author") hasattr(comment, "author")
@@ -127,11 +125,11 @@ def fetch_jira_issues_batch(
) )
continue continue
description = (jira.fields.description if JIRA_API_VERSION == "2"
else extract_text_from_adf(jira.raw["fields"]["description"]))
comments = _get_comment_strs(jira, comment_email_blacklist) comments = _get_comment_strs(jira, comment_email_blacklist)
semantic_rep = ( semantic_rep = f"{description}\n" + "\n".join(
f"{jira.fields.description}\n" [f"Comment: {comment}" for comment in comments if comment]
if jira.fields.description
else "" + "\n".join([f"Comment: {comment}" for comment in comments])
) )
page_url = f"{jira_client.client_info()}/browse/{jira.key}" page_url = f"{jira_client.client_info()}/browse/{jira.key}"