xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 20:30:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: improve line extraction from files with missing content

Browse Source
This commit is contained in:
mrT23
2024-12-27 09:00:20 +02:00
parent 12d603fdb4
commit 4aad67b563
2 changed files with 63 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
pr_agent/algo/git_patch_processing.py
View File

@ -364,7 +364,7 @@ __old hunk__
def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]: def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]:
try:
patch_with_lines_str = f"\n\n## File: '{file_name.strip()}'\n\n" patch_with_lines_str = f"\n\n## File: '{file_name.strip()}'\n\n"
selected_lines = "" selected_lines = ""
patch_lines = patch.splitlines() patch_lines = patch.splitlines()
@ -407,5 +407,8 @@ def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, s
patch_with_lines_str += line + '\n' patch_with_lines_str += line + '\n'
if not line.startswith('-'): # currently we don't support /ask line for deleted lines if not line.startswith('-'): # currently we don't support /ask line for deleted lines
selected_lines_num += 1 selected_lines_num += 1
except Exception as e:
get_logger().error(f"Failed to extract hunk lines from patch: {e}", artifact={"traceback": traceback.format_exc()})
return "", ""
return patch_with_lines_str.rstrip(), selected_lines.rstrip() return patch_with_lines_str.rstrip(), selected_lines.rstrip()

22
pr_agent/algo/utils.py
View File

@ -23,6 +23,7 @@ from pydantic import BaseModel
from starlette_context import context from starlette_context import context
from pr_agent.algo import MAX_TOKENS from pr_agent.algo import MAX_TOKENS
from pr_agent.algo.git_patch_processing import extract_hunk_lines_from_patch
from pr_agent.algo.token_handler import TokenEncoder from pr_agent.algo.token_handler import TokenEncoder
from pr_agent.algo.types import FilePatchInfo from pr_agent.algo.types import FilePatchInfo
from pr_agent.config_loader import get_settings, global_settings from pr_agent.config_loader import get_settings, global_settings
@ -272,7 +273,11 @@ def convert_to_markdown_v2(output_data: dict,
return markdown_text return markdown_text
def extract_relevant_lines_str(end_line, files, relevant_file, start_line, dedent=False):
def extract_relevant_lines_str(end_line, files, relevant_file, start_line, dedent=False) -> str:
"""
Finds 'relevant_file' in 'files', and extracts the lines from 'start_line' to 'end_line' string from the file content.
"""
try: try:
relevant_lines_str = "" relevant_lines_str = ""
if files: if files:
@ -280,10 +285,23 @@ def extract_relevant_lines_str(end_line, files, relevant_file, start_line, deden
for file in files: for file in files:
if file.filename.strip() == relevant_file: if file.filename.strip() == relevant_file:
if not file.head_file: if not file.head_file:
get_logger().warning(f"No content found in file: {file.filename}") # as a fallback, extract relevant lines directly from patch
patch = file.patch
get_logger().info(f"No content found in file: '{file.filename}' for 'extract_relevant_lines_str'. Using patch instead")
_, selected_lines = extract_hunk_lines_from_patch(patch, file.filename, start_line, end_line,side='right')
if not selected_lines:
get_logger().error(f"Failed to extract relevant lines from patch: {file.filename}")
return "" return ""
# filter out '-' lines
relevant_lines_str = ""
for line in selected_lines.splitlines():
if line.startswith('-'):
continue
relevant_lines_str += line[1:] + '\n'
else:
relevant_file_lines = file.head_file.splitlines() relevant_file_lines = file.head_file.splitlines()
relevant_lines_str = "\n".join(relevant_file_lines[start_line - 1:end_line]) relevant_lines_str = "\n".join(relevant_file_lines[start_line - 1:end_line])
if dedent and relevant_lines_str: if dedent and relevant_lines_str:
# Remove the longest leading string of spaces and tabs common to all lines. # Remove the longest leading string of spaces and tabs common to all lines.
relevant_lines_str = textwrap.dedent(relevant_lines_str) relevant_lines_str = textwrap.dedent(relevant_lines_str)