mirror of
https://github.com/qodo-ai/pr-agent.git
synced 2025-07-02 03:40:38 +08:00
279 lines
10 KiB
Python
279 lines
10 KiB
Python
from abc import ABC, abstractmethod
|
|
from dataclasses import dataclass
|
|
|
|
# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
|
|
from enum import Enum
|
|
from typing import Optional
|
|
|
|
from pr_agent.config_loader import get_settings
|
|
from pr_agent.log import get_logger
|
|
|
|
|
|
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
|
|
|
|
|
|
class GitProvider(ABC):
|
|
@abstractmethod
|
|
def is_supported(self, capability: str) -> bool:
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_diff_files(self) -> list[FilePatchInfo]:
|
|
pass
|
|
|
|
@abstractmethod
|
|
def publish_description(self, pr_title: str, pr_body: str):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_languages(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_pr_branch(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_user_id(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_pr_description_full(self) -> str:
|
|
pass
|
|
|
|
def get_pr_description(self, *, full: bool = True) -> str:
|
|
from pr_agent.config_loader import get_settings
|
|
from pr_agent.algo.utils import clip_tokens
|
|
max_tokens_description = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
|
|
description = self.get_pr_description_full() if full else self.get_user_description()
|
|
if max_tokens_description:
|
|
return clip_tokens(description, max_tokens_description)
|
|
return description
|
|
|
|
def get_user_description(self) -> str:
|
|
description = (self.get_pr_description_full() or "").strip()
|
|
description_lowercase = description.lower()
|
|
get_logger().debug(f"Existing description\n{description_lowercase}")
|
|
|
|
# if the existing description wasn't generated by the pr-agent, just return it as-is
|
|
if not self._is_generated_by_pr_agent(description_lowercase):
|
|
get_logger().debug(f"Existing description was not generated by the pr-agent")
|
|
return description
|
|
|
|
# if the existing description was generated by the pr-agent, but it doesn't contain a user description,
|
|
# return nothing (empty string) because it means there is no user description
|
|
user_description_header = "## user description"
|
|
if user_description_header not in description_lowercase:
|
|
get_logger().debug(f"Existing description was generated by the pr-agent, but it doesn't contain a user description")
|
|
return ""
|
|
|
|
# otherwise, extract the original user description from the existing pr-agent description and return it
|
|
# user_description_start_position = description_lowercase.find(user_description_header) + len(user_description_header)
|
|
# return description[user_description_start_position:].split("\n", 1)[-1].strip()
|
|
|
|
# the 'user description' is in the beginning. extract and return it
|
|
possible_headers = self._possible_headers()
|
|
start_position = description_lowercase.find(user_description_header) + len(user_description_header)
|
|
end_position = len(description)
|
|
for header in possible_headers: # try to clip at the next header
|
|
if header != user_description_header and header in description_lowercase:
|
|
end_position = min(end_position, description_lowercase.find(header))
|
|
if end_position != len(description) and end_position > start_position:
|
|
original_user_description = description[start_position:end_position].strip()
|
|
if original_user_description.endswith("___"):
|
|
original_user_description = original_user_description[:-3].strip()
|
|
else:
|
|
original_user_description = description.split("___")[0].strip()
|
|
if original_user_description.lower().startswith(user_description_header):
|
|
original_user_description = original_user_description[len(user_description_header):].strip()
|
|
|
|
get_logger().debug(f"Extracted user description from existing description\n{original_user_description}")
|
|
return original_user_description
|
|
|
|
def _possible_headers(self):
|
|
return ("## user description", "## pr type", "## pr description", "## pr labels", "## type", "## description",
|
|
"## labels", "### 🤖 generated by pr agent")
|
|
|
|
def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
|
|
possible_headers = self._possible_headers()
|
|
return any(description_lowercase.startswith(header) for header in possible_headers)
|
|
|
|
@abstractmethod
|
|
def get_repo_settings(self):
|
|
pass
|
|
|
|
def get_pr_id(self):
|
|
return ""
|
|
|
|
def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
|
|
return ""
|
|
|
|
#### comments operations ####
|
|
@abstractmethod
|
|
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
|
pass
|
|
|
|
def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool):
|
|
self.publish_comment(pr_comment)
|
|
|
|
@abstractmethod
|
|
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
|
pass
|
|
|
|
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
|
|
absolute_position: int = None):
|
|
raise NotImplementedError("This git provider does not support creating inline comments yet")
|
|
|
|
@abstractmethod
|
|
def publish_inline_comments(self, comments: list[dict]):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def remove_initial_comment(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def remove_comment(self, comment):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_issue_comments(self):
|
|
pass
|
|
|
|
def get_comment_url(self, comment) -> str:
|
|
return ""
|
|
|
|
#### labels operations ####
|
|
@abstractmethod
|
|
def publish_labels(self, labels):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_pr_labels(self):
|
|
pass
|
|
|
|
def get_repo_labels(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
|
|
pass
|
|
|
|
@abstractmethod
|
|
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
|
pass
|
|
|
|
#### commits operations ####
|
|
@abstractmethod
|
|
def get_commit_messages(self):
|
|
pass
|
|
|
|
def get_latest_commit_url(self) -> str:
|
|
return ""
|
|
|
|
def get_main_pr_language(languages, files) -> str:
|
|
"""
|
|
Get the main language of the commit. Return an empty string if cannot determine.
|
|
"""
|
|
main_language_str = ""
|
|
if not languages:
|
|
get_logger().info("No languages detected")
|
|
return main_language_str
|
|
if not files:
|
|
get_logger().info("No files in diff")
|
|
return main_language_str
|
|
|
|
try:
|
|
top_language = max(languages, key=languages.get).lower()
|
|
|
|
# validate that the specific commit uses the main language
|
|
extension_list = []
|
|
for file in files:
|
|
if not file:
|
|
continue
|
|
if isinstance(file, str):
|
|
file = FilePatchInfo(base_file=None, head_file=None, patch=None, filename=file)
|
|
extension_list.append(file.filename.rsplit('.')[-1])
|
|
|
|
# get the most common extension
|
|
most_common_extension = '.' + max(set(extension_list), key=extension_list.count)
|
|
try:
|
|
language_extension_map_org = get_settings().language_extension_map_org
|
|
language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
|
|
|
|
if top_language in language_extension_map and most_common_extension in language_extension_map[top_language]:
|
|
main_language_str = top_language
|
|
else:
|
|
for language, extensions in language_extension_map.items():
|
|
if most_common_extension in extensions:
|
|
main_language_str = language
|
|
break
|
|
except Exception as e:
|
|
get_logger().exception(f"Failed to get main language: {e}")
|
|
pass
|
|
|
|
## old approach:
|
|
# most_common_extension = max(set(extension_list), key=extension_list.count)
|
|
# if most_common_extension == 'py' and top_language == 'python' or \
|
|
# most_common_extension == 'js' and top_language == 'javascript' or \
|
|
# most_common_extension == 'ts' and top_language == 'typescript' or \
|
|
# most_common_extension == 'tsx' and top_language == 'typescript' or \
|
|
# most_common_extension == 'go' and top_language == 'go' or \
|
|
# most_common_extension == 'java' and top_language == 'java' or \
|
|
# most_common_extension == 'c' and top_language == 'c' or \
|
|
# most_common_extension == 'cpp' and top_language == 'c++' or \
|
|
# most_common_extension == 'cs' and top_language == 'c#' or \
|
|
# most_common_extension == 'swift' and top_language == 'swift' or \
|
|
# most_common_extension == 'php' and top_language == 'php' or \
|
|
# most_common_extension == 'rb' and top_language == 'ruby' or \
|
|
# most_common_extension == 'rs' and top_language == 'rust' or \
|
|
# most_common_extension == 'scala' and top_language == 'scala' or \
|
|
# most_common_extension == 'kt' and top_language == 'kotlin' or \
|
|
# most_common_extension == 'pl' and top_language == 'perl' or \
|
|
# most_common_extension == top_language:
|
|
# main_language_str = top_language
|
|
|
|
except Exception as e:
|
|
get_logger().exception(e)
|
|
pass
|
|
|
|
return main_language_str
|
|
|
|
|
|
class IncrementalPR:
|
|
def __init__(self, is_incremental: bool = False):
|
|
self.is_incremental = is_incremental
|
|
self.commits_range = None
|
|
self.first_new_commit = None
|
|
self.last_seen_commit = None
|
|
|
|
@property
|
|
def first_new_commit_sha(self):
|
|
return None if self.first_new_commit is None else self.first_new_commit.sha
|
|
|
|
@property
|
|
def last_seen_commit_sha(self):
|
|
return None if self.last_seen_commit is None else self.last_seen_commit.sha
|