Merge pull request #638 from Codium-ai/tr/describe_bullets

insert_br_after_x_chars

pr_agent/algo/git_patch_processing.py

@@ -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
 
 

pr_agent/algo/pr_processing.py

@@ -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,

pr_agent/algo/types.py

@@ -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

pr_agent/algo/utils.py

@@ -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

pr_agent/git_providers/azuredevops_provider.py

@@ -6,7 +6,8 @@ from ..log import get_logger
 from ..algo.language_handler import is_valid_file
 from ..algo.utils import clip_tokens, load_large_diff
 from ..config_loader import get_settings
-from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from .git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 
 AZURE_DEVOPS_AVAILABLE = True
 

pr_agent/git_providers/bitbucket_provider.py

@@ -6,10 +6,11 @@ import requests
 from atlassian.bitbucket import Cloud
 from starlette_context import context
 
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from pr_agent.algo.types import FilePatchInfo, EDIT_TYPE
+from ..algo.utils import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
-from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+from .git_provider import GitProvider
 
 
 class BitbucketProvider(GitProvider):

pr_agent/git_providers/bitbucket_server_provider.py

@@ -6,9 +6,9 @@ import requests
 from atlassian.bitbucket import Bitbucket
 from starlette_context import context
 
-from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+from .git_provider import GitProvider
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from pr_agent.algo.types import FilePatchInfo
-from ..algo.utils import load_large_diff
+from ..algo.utils import load_large_diff, find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
 

pr_agent/git_providers/codecommit_provider.py

@@ -5,9 +5,9 @@ from typing import List, Optional, Tuple
 from urllib.parse import urlparse
 
 from pr_agent.git_providers.codecommit_client import CodeCommitClient
-
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 from ..algo.utils import load_large_diff
-from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from .git_provider import GitProvider
 from ..config_loader import get_settings
 from ..log import get_logger
 

pr_agent/git_providers/gerrit_provider.py

@@ -13,7 +13,8 @@ import urllib3.util
 from git import Repo
 
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from pr_agent.git_providers.git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 from pr_agent.git_providers.local_git_provider import PullRequestMimic
 from pr_agent.log import get_logger
 

pr_agent/git_providers/git_provider.py

@@ -1,35 +1,13 @@
 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.algo.types import FilePatchInfo
 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:

pr_agent/git_providers/github_provider.py

@@ -9,12 +9,12 @@ from retry import retry
 from starlette_context import context
 
 from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
-from ..algo.utils import load_large_diff, clip_tokens
 from ..config_loader import get_settings
 from ..log import get_logger
 from ..servers.utils import RateLimitExceeded
-from .git_provider import FilePatchInfo, GitProvider, IncrementalPR, EDIT_TYPE
+from .git_provider import GitProvider, IncrementalPR
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 
 
 class GithubProvider(GitProvider):

pr_agent/git_providers/gitlab_provider.py

@@ -7,10 +7,10 @@ import gitlab
 from gitlab import GitlabGetError
 
 from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
-from ..algo.utils import load_large_diff, clip_tokens
 from ..config_loader import get_settings
-from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from .git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 from ..log import get_logger
 
 

pr_agent/git_providers/local_git_provider.py

@@ -5,7 +5,8 @@ from typing import List
 from git import Repo
 
 from pr_agent.config_loader import _find_repository_root, get_settings
-from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+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
 
 

pr_agent/settings/configuration.toml

@@ -9,11 +9,11 @@ verbosity_level=0 # 0,1,2
 use_extra_bad_extensions=false
 use_repo_settings_file=true
 use_global_settings_file=true
-ai_timeout=180
+ai_timeout=90
 max_description_tokens = 500
 max_commits_tokens = 500
 max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
-patch_extra_lines = 3
+patch_extra_lines = 1
 secret_provider="google_cloud_storage"
 cli_mode=false
 

pr_agent/tools/pr_code_suggestions.py

@@ -325,7 +325,7 @@ class PRCodeSuggestions:
 
             pr_body += "<table>"
             header = f"Suggestions"
-            delta = 77
+            delta = 75
             header += "&nbsp; " * delta
             pr_body += f"""<thead><tr><th></th><th>{header}</th></tr></thead>"""
             pr_body += """<tbody>"""

pr_agent/tools/pr_description.py

@@ -9,7 +9,7 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels
+from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels, ModelType
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
@@ -80,7 +80,7 @@ class PRDescription:
             if get_settings().config.publish_output:
                 self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)
 
-            await retry_with_fallback_models(self._prepare_prediction)
+            await retry_with_fallback_models(self._prepare_prediction, ModelType.TURBO) # turbo model because larger context
 
             get_logger().info(f"Preparing answer {self.pr_id}")
             if self.prediction:
@@ -363,7 +363,7 @@ class PRDescription:
         try:
             pr_body += "<table>"
             header = f"Relevant files"
-            delta = 77
+            delta = 75
             # header += "&nbsp; " * delta
             pr_body += f"""<thead><tr><th></th><th align="left">{header}</th></tr></thead>"""
             pr_body += """<tbody>"""
@@ -379,8 +379,7 @@ class PRDescription:
                 for filename, file_changes_title, file_change_description in list_tuples:
                     filename = filename.replace("'", "`")
                     filename_publish = filename.split("/")[-1]
-                    file_changes_title_br = insert_br_after_x_chars(file_changes_title, x=(delta - 5),
+                    file_changes_title_br = insert_br_after_x_chars(file_changes_title, x=(delta - 5))
-                                                                    new_line_char="\n\n")
                     file_changes_title_extended = file_changes_title_br.strip() + "</code>"
                     if len(file_changes_title_extended) < (delta - 5):
                         file_changes_title_extended += "&nbsp; " * ((delta - 5) - len(file_changes_title_extended))
@@ -428,48 +427,74 @@ class PRDescription:
             pass
         return pr_body
 
-def insert_br_after_x_chars(text, x=70, new_line_char="<br> "):
+def insert_br_after_x_chars(text, x=70):
     """
     Insert <br> into a string after a word that increases its length above x characters.
+    Use proper HTML tags for code and new lines.
     """
     if len(text) < x:
         return text
 
-    lines = text.splitlines()
+    # replace odd instances of ` with <code> and even instances of ` with </code>
+    text = replace_code_tags(text)
+
+    # convert list items to <li>
+    if text.startswith("- "):
+        text = "<li>" + text[2:]
+    text = text.replace("\n- ", '<br><li> ').replace("\n - ", '<br><li> ')
+
+    # convert new lines to <br>
+    text = text.replace("\n", '<br>')
+
+    # split text into lines
+    lines = text.split('<br>')
     words = []
-    for i,line in enumerate(lines):
+    for i, line in enumerate(lines):
         words += line.split(' ')
-        if i<len(lines)-1:
+        if i < len(lines) - 1:
-            words[-1] += "\n"
+            words[-1] += "<br>"
 
+    def count_chars_without_html(string):
+        if '<' not in string:
+            return len(string)
+        no_html_string = re.sub('<[^>]+>', '', string)
+        return len(no_html_string)
 
-    # words = text.split(' ')
+    new_text = []
-
-    new_text = ""
-    current_length = 0
     is_inside_code = False
+    current_length = 0
     for word in words:
-        # Check if adding this word exceeds x characters
+        is_saved_word = False
-        if current_length + len(word) > x:
+        if word == "<code>" or word == "</code>" or word == "<li>" or word == "<br>":
-            if not is_inside_code:
+            is_saved_word = True
-                new_text += f"{new_line_char} "  # Insert line break
+        if "<code>" in word:
-                current_length = 0  # Reset counter
-            else:
-                new_text += f"`{new_line_char} `"
-        # check if inside <code> tag
-        if word.startswith("`") and not is_inside_code and not word.endswith("`"):
             is_inside_code = True
-        if word.endswith("`"):
+        if  "</code>" in word:
             is_inside_code = False
 
-        # Add the word to the new text
+        len_word = count_chars_without_html(word)
-        if word.endswith("\n"):
+        if not is_saved_word and (current_length + len_word > x):
-            new_text += word
+            if is_inside_code:
-        else:
+                new_text.append("</code><br><code>")
-            new_text += word + " "
+            else:
-        current_length += len(word) + 1  # Add 1 for the space
+                new_text.append("<br>")
+            current_length = 0  # Reset counter
+        new_text.append(word + " ")
 
+        if not is_saved_word:
+            current_length += len_word + 1  # Add 1 for the space
 
-        if word.endswith("\n"):
+        if word == "<li>" or word == "<br>":
             current_length = 0
-    return new_text.strip()  # Remove trailing space
+
+    return ''.join(new_text).strip()
+
+def replace_code_tags(text):
+    """
+    Replace odd instances of ` with <code> and even instances of ` with </code>
+    """
+    parts = text.split('`')
+    for i in range(1, len(parts), 2):
+        parts[i] = '<code>' + parts[i] + '</code>'
+    return ''.join(parts)
+

tests/unittest/test_codecommit_provider.py

@@ -3,7 +3,7 @@ from unittest.mock import patch
 from pr_agent.git_providers.codecommit_provider import CodeCommitFile
 from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
 from pr_agent.git_providers.codecommit_provider import PullRequestCCMimic
-from pr_agent.git_providers.git_provider import EDIT_TYPE
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 
 
 class TestCodeCommitFile:

tests/unittest/test_convert_to_markdown.py

@@ -1,5 +1,6 @@
 # Generated by CodiumAI
 from pr_agent.algo.utils import convert_to_markdown
+from pr_agent.tools.pr_description import insert_br_after_x_chars
 
 """
 Code Analysis
@@ -93,3 +94,27 @@ class TestConvertToMarkdown:
         }
         expected_output = ''
         assert convert_to_markdown(input_data).strip() == expected_output.strip()
+
+
+class TestBR:
+    def test_br1(self):
+        file_change_description = '- Imported `FilePatchInfo` and `EDIT_TYPE` from `pr_agent.algo.types` instead of `pr_agent.git_providers.git_provider`.'
+        file_change_description_br = insert_br_after_x_chars(file_change_description)
+        expected_output = ('<li>Imported <code>FilePatchInfo</code> and <code>EDIT_TYPE</code> from '
+                           '<code>pr_agent.algo.types</code> instead <br>of '
+                           '<code>pr_agent.git_providers.git_provider</code>.')
+        assert file_change_description_br == expected_output
+        # print("-----")
+        # print(file_change_description_br)
+
+    def test_br2(self):
+        file_change_description = ('- Created a - new -class `ColorPaletteResourcesCollection ColorPaletteResourcesCollection '
+                                   'ColorPaletteResourcesCollection ColorPaletteResourcesCollection`')
+        file_change_description_br = insert_br_after_x_chars(file_change_description)
+        expected_output = ('<li>Created a - new -class <code>ColorPaletteResourcesCollection </code><br><code>'
+                           'ColorPaletteResourcesCollection ColorPaletteResourcesCollection <br>'
+                           'ColorPaletteResourcesCollection</code>')
+        assert file_change_description_br == expected_output
+        # print("-----")
+        # print(file_change_description_br)
+

tests/unittest/test_find_line_number_of_relevant_line_in_file.py

@@ -1,8 +1,7 @@
 
 # Generated by CodiumAI
-from pr_agent.git_providers.git_provider import FilePatchInfo
+from pr_agent.algo.types import FilePatchInfo
-from pr_agent.algo.pr_processing import find_line_number_of_relevant_line_in_file
+from pr_agent.algo.utils import find_line_number_of_relevant_line_in_file
-
 
 import pytest