xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-10 07:40:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into patch-1

Browse Source
This commit is contained in:
Ori Kotek
2023-08-06 18:09:09 +03:00
parent 703215fe83 a45343793a
commit a00038fbd8
12 changed files with 347 additions and 142 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
pr_agent/algo/pr_processing.py
View File

@ -1,7 +1,10 @@
from __future__ import annotations
import traceback
import difflib
import logging
from typing import Callable, Tuple
import re
import traceback
from typing import Any, Callable, List, Tuple
from github import RateLimitExceededException
@ -9,9 +12,8 @@ from pr_agent.algo import MAX_TOKENS
from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
from pr_agent.algo.language_handler import sort_files_by_main_languages
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import load_large_diff
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import GitProvider
from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
DELETED_FILES_ = "Deleted files:\n"
@ -46,7 +48,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
PATCH_EXTRA_LINES = 0
try:
diff_files = list(git_provider.get_diff_files())
diff_files = git_provider.get_diff_files()
except RateLimitExceededException as e:
logging.error(f"Rate limit exceeded for git provider API. original message {e}")
raise
@ -98,12 +100,7 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
for lang in pr_languages:
for file in lang['files']:
original_file_content_str = file.base_file
new_file_content_str = file.head_file
patch = file.patch
# handle the case of large patch, that initially was not loaded
patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
if not patch:
continue
@ -161,7 +158,6 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
original_file_content_str = file.base_file
new_file_content_str = file.head_file
patch = file.patch
patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
if not patch:
continue
@ -224,3 +220,67 @@ async def retry_with_fallback_models(f: Callable):
logging.warning(f"Failed to generate prediction with {model}: {traceback.format_exc()}")
if i == len(all_models) - 1: # If it's the last iteration
raise # Re-raise the last exception
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(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
for file in diff_files:
if file.filename.strip() == relevant_file:
patch = file.patch
patch_lines = patch.splitlines()
# 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,
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)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
if relevant_line_in_file in line and line[0] != '-':
position = i
absolute_position = start2 + delta - 1
break
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)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
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
break
return position, absolute_position

41
pr_agent/algo/utils.py
View File

@ -40,7 +40,7 @@ def convert_to_markdown(output_data: dict) -> str:
"Security concerns": "🔒",
"General PR suggestions": "💡",
"Insights from user's answers": "📝",
"Code suggestions": "🤖",
"Code feedback": "🤖",
}
for key, value in output_data.items():
@ -50,12 +50,12 @@ def convert_to_markdown(output_data: dict) -> str:
markdown_text += f"## {key}\n\n"
markdown_text += convert_to_markdown(value)
elif isinstance(value, list):
if key.lower() == 'code suggestions':
if key.lower() == 'code feedback':
markdown_text += "\n" # just looks nicer with additional line breaks
emoji = emojis.get(key, "")
markdown_text += f"- {emoji} **{key}:**\n\n"
for item in value:
if isinstance(item, dict) and key.lower() == 'code suggestions':
if isinstance(item, dict) and key.lower() == 'code feedback':
markdown_text += parse_code_suggestion(item)
elif item:
markdown_text += f" - {item}\n"
@ -100,7 +100,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
Args:
- review: A string containing the JSON message to be fixed.
- max_iter: An integer representing the maximum number of iterations to try and fix the JSON message.
- code_suggestions: A boolean indicating whether to try and fix JSON messages with code suggestions.
- code_suggestions: A boolean indicating whether to try and fix JSON messages with code feedback.
Returns:
- data: A dictionary containing the parsed JSON data.
@ -108,7 +108,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
The function attempts to fix broken or incomplete JSON messages by parsing until the last valid code suggestion.
If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the
message.
If code_suggestions is True and the JSON message contains code suggestions, the function tries to fix the JSON
If code_suggestions is True and the JSON message contains code feedback, the function tries to fix the JSON
message by parsing until the last valid code suggestion.
The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or
newlines.
@ -128,7 +128,8 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
else:
closing_bracket = "]}}"
if review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0:
if (review.rfind("'Code feedback': [") > 0 or review.rfind('"Code feedback": [') > 0) or \
(review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0) :
last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
valid_json = False
iter_count = 0
@ -195,38 +196,30 @@ def convert_str_to_datetime(date_str):
return datetime.strptime(date_str, datetime_format)
def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str:
def load_large_diff(filename, new_file_content_str: str, original_file_content_str: str) -> str:
"""
Generate a patch for a modified file by comparing the original content of the file with the new content provided as
input.
Args:
file: The file object for which the patch needs to be generated.
new_file_content_str: The new content of the file as a string.
original_file_content_str: The original content of the file as a string.
patch: An optional patch string that can be provided as input.
Returns:
The generated or provided patch string.
Raises:
None.
Additional Information:
- If 'patch' is not provided as input, the function generates a patch using the 'difflib' library and returns it
as output.
- If the 'settings.config.verbosity_level' is greater than or equal to 2, a warning message is logged indicating
that the file was modified but no patch was found, and a patch is manually created.
"""
if not patch: # to Do - also add condition for file extension
try:
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
new_file_content_str.splitlines(keepends=True))
if get_settings().config.verbosity_level >= 2:
logging.warning(f"File was modified, but no patch was found. Manually creating patch: {file.filename}.")
patch = ''.join(diff)
except Exception:
pass
patch = ""
try:
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
new_file_content_str.splitlines(keepends=True))
if get_settings().config.verbosity_level >= 2:
logging.warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
patch = ''.join(diff)
except Exception:
pass
return patch