xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-04 04:40:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

TestFindLineNumberOfRelevantLineInFile

Browse Source
This commit is contained in:
mrT23
2023-08-06 08:31:15 +03:00
parent fed0ea349a
commit 7367c62cf9
2 changed files with 93 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
pr_agent/algo/pr_processing.py
View File

@ -3,7 +3,7 @@ from __future__ import annotations
import re
import difflib
import logging
from typing import Callable, Tuple, List, Any, Sequence
from typing import Callable, Tuple, List, Any
from github import RateLimitExceededException
from pr_agent.algo import MAX_TOKENS
@ -220,12 +220,25 @@ async def retry_with_fallback_models(f: Callable):
raise # Re-raise the last exception
def find_line_number_of_relevant_line_in_file(diff_files: list[FilePatchInfo], relevant_file: str,
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
relevant_file: str,
relevant_line_in_file: str) -> Tuple[int, int]:
"""
Find the line number and absolute position of a relevant line in a file.
Args:
diff_files (List[FilePatchInfo]): A list of FilePatchInfo objects representing the patches of files.
relevant_file (str): The name of the file where the relevant line is located.
relevant_line_in_file (str): The content of the relevant line.
Returns:
Tuple[int, int]: A tuple containing the line number and absolute position of the relevant line in the file.
"""
position = -1
absolute_position = -1
RE_HUNK_HEADER = re.compile(
re_hunk_header = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
for file in diff_files:
if file.filename.strip() == relevant_file:
patch = file.patch
@ -233,16 +246,16 @@ def find_line_number_of_relevant_line_in_file(diff_files: list[FilePatchInfo], r
# try to find the line in the patch using difflib, with some margin of error
matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
file.patch.splitlines(), n=3, cutoff=0.95)
patch_lines, n=3, cutoff=0.93)
if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
relevant_line_in_file = matches_difflib[0]
delta = 0
start1, size1, start2, size2 = 0, 0, 0, 0
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
delta = 0
match = RE_HUNK_HEADER.match(line)
match = re_hunk_header.match(line)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
@ -251,18 +264,19 @@ def find_line_number_of_relevant_line_in_file(diff_files: list[FilePatchInfo], r
position = i
absolute_position = start2 + delta - 1
break
if position == -1:
if position == -1 and relevant_line_in_file[0] == '+':
no_plus_line = relevant_line_in_file[1:].lstrip()
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
delta = 0
match = RE_HUNK_HEADER.match(line)
match = re_hunk_header.match(line)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
if relevant_line_in_file[0] == '+' and relevant_line_in_file[1:].lstrip() in line and line[
0] != '-':
# The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
if no_plus_line in line and line[0] != '-':
# The model might add a '+' to the beginning of the relevant_line_in_file even if originally
# it's a context line
position = i
absolute_position = start2 + delta - 1