xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 20:00:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

insert_br_after_x_chars

Browse Source
This commit is contained in:
mrT23
2024-02-05 09:20:36 +02:00
parent e104bd7a3f
commit 2ee329674f
17 changed files with 200 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pr_agent/algo/git_patch_processing.py
View File

@ -3,7 +3,7 @@ from __future__ import annotations
import re
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import EDIT_TYPE
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
from pr_agent.log import get_logger

79
pr_agent/algo/pr_processing.py
View File

@ -1,9 +1,7 @@
from __future__ import annotations
import difflib
import re
import traceback
from typing import Any, Callable, List, Tuple
from typing import Callable, List, Tuple
from github import RateLimitExceededException
@ -13,7 +11,8 @@ from pr_agent.algo.file_filter import filter_ignored
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import get_max_tokens, ModelType
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
from pr_agent.git_providers.git_provider import GitProvider
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
from pr_agent.log import get_logger
DELETED_FILES_ = "Deleted files:\n"
@ -270,78 +269,6 @@ def _get_all_deployments(all_models: List[str]) -> List[str]:
return all_deployments
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
relevant_file: str,
relevant_line_in_file: str,
absolute_position: int = None) -> Tuple[int, int]:
position = -1
if absolute_position is None:
absolute_position = -1
re_hunk_header = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
for file in diff_files:
if file.filename and (file.filename.strip() == relevant_file):
patch = file.patch
patch_lines = patch.splitlines()
delta = 0
start1, size1, start2, size2 = 0, 0, 0, 0
if absolute_position != -1: # matching absolute to relative
for i, line in enumerate(patch_lines):
# new hunk
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
#
absolute_position_curr = start2 + delta - 1
if absolute_position_curr == absolute_position:
position = i
break
else:
# 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]
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
def get_pr_multi_diffs(git_provider: GitProvider,
token_handler: TokenHandler,
model: str,

23
pr_agent/algo/types.py Normal file
View File

@ -0,0 +1,23 @@
from dataclasses import dataclass
from enum import Enum
class EDIT_TYPE(Enum):
ADDED = 1
DELETED = 2
MODIFIED = 3
RENAMED = 4
UNKNOWN = 5
@dataclass
class FilePatchInfo:
base_file: str
head_file: str
patch: str
filename: str
tokens: int = -1
edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN
old_filename: str = None
num_plus_lines: int = -1
num_minus_lines: int = -1

77
pr_agent/algo/utils.py
View File

@ -6,7 +6,7 @@ import re
import textwrap
from datetime import datetime
from enum import Enum
from typing import Any, List
from typing import Any, List, Tuple
import yaml
from starlette_context import context
@ -14,6 +14,7 @@ from starlette_context import context
from pr_agent.algo import MAX_TOKENS
from pr_agent.algo.token_handler import get_token_encoder
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.algo.types import FilePatchInfo
from pr_agent.log import get_logger
class ModelType(str, Enum):
@ -487,4 +488,76 @@ def replace_code_tags(text):
parts = text.split('`')
for i in range(1, len(parts), 2):
parts[i] = '<code>' + parts[i] + '</code>'
return ''.join(parts)
return ''.join(parts)
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
relevant_file: str,
relevant_line_in_file: str,
absolute_position: int = None) -> Tuple[int, int]:
position = -1
if absolute_position is None:
absolute_position = -1
re_hunk_header = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
for file in diff_files:
if file.filename and (file.filename.strip() == relevant_file):
patch = file.patch
patch_lines = patch.splitlines()
delta = 0
start1, size1, start2, size2 = 0, 0, 0, 0
if absolute_position != -1: # matching absolute to relative
for i, line in enumerate(patch_lines):
# new hunk
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
#
absolute_position_curr = start2 + delta - 1
if absolute_position_curr == absolute_position:
position = i
break
else:
# 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]
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