bioguider 0.2.3__py3-none-any.whl

bioguider/utils/gitignore_checker.py

@@ -0,0 +1,175 @@
+import fnmatch
+import os
+from pathlib import Path
+from typing import Callable
+
+class GitignoreChecker:
+    def __init__(
+        self, 
+        directory: str, 
+        gitignore_path: str,
+        exclude_dir_patterns: list[str] | None = None,
+        exclude_file_patterns: list[str] | None = None
+    ):
+        """
+        Initialize the GitignoreChecker with a specific directory and the path to a .gitignore file.
+
+        Args:
+            directory (str): The directory to be checked.
+            gitignore_path (str): The path to the .gitignore file.
+        """
+        self.directory = directory
+        self.gitignore_path = gitignore_path
+        self.folder_patterns, self.file_patterns = self._load_gitignore_patterns()
+        self.exclude_dir_patterns = exclude_dir_patterns
+        self.exclude_file_patterns = exclude_file_patterns
+
+    def _load_gitignore_patterns(self) -> tuple:
+        """
+        Load and parse the .gitignore file, then split the patterns into folder and file patterns.
+
+        If the specified .gitignore file is not found, fall back to the default path.
+
+        Returns:
+            tuple: A tuple containing two lists - one for folder patterns and one for file patterns.
+        """
+        try:
+            with open(self.gitignore_path, "r", encoding="utf-8") as file:
+                gitignore_content = file.read()
+        except FileNotFoundError:
+            # Fallback to the default .gitignore path if the specified file is not found
+            default_path = os.path.join(
+                os.path.dirname(__file__), "default.gitignore"
+            )
+            with open(default_path, "r", encoding="utf-8") as file:
+                gitignore_content = file.read()
+
+        patterns = self._parse_gitignore(gitignore_content)
+        return self._split_gitignore_patterns(patterns)
+
+    @staticmethod
+    def _parse_gitignore(gitignore_content: str) -> list:
+        """
+        Parse the .gitignore content and return patterns as a list.
+
+        Args:
+            gitignore_content (str): The content of the .gitignore file.
+
+        Returns:
+            list: A list of patterns extracted from the .gitignore content.
+        """
+        patterns = []
+        for line in gitignore_content.splitlines():
+            line = line.strip()
+            if line and not line.startswith("#"):
+                patterns.append(line)
+        return patterns
+
+    @staticmethod
+    def _split_gitignore_patterns(gitignore_patterns: list) -> tuple:
+        """
+        Split the .gitignore patterns into folder patterns and file patterns.
+
+        Args:
+            gitignore_patterns (list): A list of patterns from the .gitignore file.
+
+        Returns:
+            tuple: Two lists, one for folder patterns and one for file patterns.
+        """
+        folder_patterns = []
+        file_patterns = []
+        for pattern in gitignore_patterns:
+            if pattern.endswith("/"):
+                folder_patterns.append(pattern.rstrip("/"))
+            else:
+                file_patterns.append(pattern)
+        return folder_patterns, file_patterns
+
+    @staticmethod
+    def _is_ignored(path: str, patterns: list, is_dir: bool = False) -> bool:
+        """
+        Check if the given path matches any of the patterns.
+
+        Args:
+            path (str): The path to check.
+            patterns (list): A list of patterns to check against.
+            is_dir (bool): True if the path is a directory, False otherwise.
+
+        Returns:
+            bool: True if the path matches any pattern, False otherwise.
+        """
+        for pattern in patterns:
+            if fnmatch.fnmatch(path, pattern):
+                return True
+            if is_dir and pattern.endswith("/") and fnmatch.fnmatch(path, pattern[:-1]):
+                return True
+        return False
+    
+    @staticmethod
+    def _is_ignored_by_default(path: str, is_dir: bool=False) -> bool:
+        return is_dir and path.startswith(".") # path == ".git" 
+
+
+    def _is_ignored_by_exclude_file_patterns(self, f: str):
+        if self.exclude_file_patterns is None:
+            return False
+        return True if self._is_ignored(f, self.exclude_file_patterns) else False
+
+
+    def check_files_and_folders(
+        self, 
+        level=-1, 
+        check_file_cb: Callable[[str, str], bool] | None = None
+    ) -> list:
+        """
+        Check all files and folders in the given directory against the split gitignore patterns.
+        Return a list of files that are not ignored.
+        The returned file paths are relative to the self.directory.
+
+        Returns:
+            list: A list of paths to files that are not ignored.
+        """
+        not_ignored_files = []
+        root_path = Path(self.directory)
+        for root, dirs, files in os.walk(self.directory):
+            current_root_path = Path(root)
+            current_levels = len(current_root_path.relative_to(root_path).parts)
+            if level >= 0 and current_levels > level:
+                continue
+            dirs[:] = [
+                d
+                for d in dirs
+                if not self._is_ignored(d, self.folder_patterns, is_dir=True) \
+                and not self._is_ignored_by_default(d, True)
+            ]
+            if self.exclude_dir_patterns:
+                dirs[:] = [
+                    d
+                    for d in dirs
+                    if not self._is_ignored(d, self.exclude_dir_patterns, is_dir=True)
+                ]
+
+            for file in files:
+                file_path = os.path.join(root, file)
+                relative_path = os.path.relpath(file_path, self.directory)
+                if not self._is_ignored(
+                    file, self.file_patterns
+                ) and not self._is_ignored_by_exclude_file_patterns(file):
+                    if check_file_cb is None:
+                        not_ignored_files.append(relative_path)
+                    else:
+                        if check_file_cb(self.directory, relative_path):
+                            not_ignored_files.append(relative_path)
+            
+            if level >= 0 and current_levels == level:
+                not_ignored_files = \
+                    not_ignored_files + \
+                    [os.path.relpath(os.path.join(root, d), self.directory) for d in dirs]
+
+        return not_ignored_files
+
+
+# Example usage:
+# gitignore_checker = GitignoreChecker('path_to_directory', 'path_to_gitignore_file')
+# not_ignored_files = gitignore_checker.check_files_and_folders()
+# print(not_ignored_files)

bioguider/utils/pyphen_utils.py

@@ -0,0 +1,73 @@
+
+import os
+import re
+import pyphen
+import math
+
+class PyphenReadability:
+    def __init__(self, lang='en'):
+        self.dic = pyphen.Pyphen(lang=lang)
+
+    def count_syllables(self, word):
+        return self.dic.inserted(word).count('-') + 1 if word.isalpha() else 0
+    
+    def extract_urls(self, text):
+        """Find all URLs in the text."""
+        url_pattern = r'https?://\S+|www\.\S+'
+        return re.findall(url_pattern, text)
+    
+    def remove_urls(self, text):
+        """Remove URLs from text for clean sentence splitting."""
+        url_pattern = r'https?://\S+|www\.\S+'
+        return re.sub(url_pattern, '', text)
+    
+    def split_sentences(self, text):
+        """Split into sentences using punctuation."""
+        return re.split(r'[.!?]+', text)
+    
+    def split_words(self, text):
+        """Extract words."""
+        return re.findall(r'\b\w+\b', text)
+    
+    def is_polysyllabic(self, word):
+        return self.count_syllables(word) >= 3
+    
+    def is_complex(self, word):
+        return self.is_polysyllabic(word)
+    
+    def readability_metrics(self, text):
+        # Extract and remove URLs
+        urls = self.extract_urls(text)
+        url_count = len(urls)
+        text_without_urls = self.remove_urls(text)
+    
+        # Split and count
+        sentences = [s for s in self.split_sentences(text_without_urls) if s.strip()]
+        sentence_count = len(sentences) + url_count
+    
+        words = self.split_words(text) # split_words(text_without_urls)
+        word_count = len(words)
+    
+        syllable_count = sum(self.count_syllables(w) for w in words)
+        polysyllables = sum(1 for w in words if self.is_polysyllabic(w))
+        complex_words = sum(1 for w in words if self.is_complex(w))
+    
+        # Avoid division by zero
+        words_per_sentence = word_count / sentence_count if sentence_count > 0 else 0
+        syllables_per_word = syllable_count / word_count if word_count > 0 else 0
+        complex_per_word = complex_words / word_count if word_count > 0 else 0
+    
+        # Readability formulas
+        flesch_reading_ease = 206.835 - 1.015 * words_per_sentence - 84.6 * syllables_per_word
+        flesch_kincaid_grade = 0.39 * words_per_sentence + 11.8 * syllables_per_word - 15.59
+        gunning_fog_index = 0.4 * (words_per_sentence + 100 * complex_per_word)
+        smog_index = (
+            1.043 * math.sqrt(polysyllables * (30 / sentence_count)) + 3.1291
+            if sentence_count >= 1 else 0
+        )
+    
+        return flesch_reading_ease, flesch_kincaid_grade, gunning_fog_index, smog_index,\
+             sentence_count, word_count, syllable_count, polysyllables, complex_words
+    
+
+    

bioguider/utils/utils.py

@@ -0,0 +1,27 @@
+import logging
+import tiktoken
+logger = logging.getLogger(__name__)
+
+def count_tokens(text: str, local_ollama: bool = False) -> int:
+    """
+    Count the number of tokens in a text string using tiktoken.
+
+    Args:
+        text (str): The text to count tokens for.
+        local_ollama (bool, optional): Whether using local Ollama embeddings. Default is False.
+
+    Returns:
+        int: The number of tokens in the text.
+    """
+    try:
+        if local_ollama:
+            encoding = tiktoken.get_encoding("cl100k_base")
+        else:
+            encoding = tiktoken.encoding_for_model("text-embedding-3-small")
+
+        return len(encoding.encode(text))
+    except Exception as e:
+        # Fallback to a simple approximation if tiktoken fails
+        logger.warning(f"Error counting tokens with tiktoken: {e}")
+        # Rough approximation: 4 characters per token
+        return len(text) // 4

bioguider-0.2.3.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 OSU_BMBL
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

bioguider-0.2.3.dist-info/METADATA

@@ -0,0 +1,44 @@
+Metadata-Version: 2.3
+Name: bioguider
+Version: 0.2.3
+Summary: An AI-Powered package to help biomedical developers to generate clear documentation
+License: MIT
+Author: Cankun Wang
+Author-email: Cankun.Wang@osumc.edu
+Requires-Python: >=3.11,<4.0
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Dist: adalflow (>=1.0.4,<2.0.0)
+Requires-Dist: binaryornot (>=0.4.4,<0.5.0)
+Requires-Dist: faiss-cpu (>=1.11.0,<2.0.0)
+Requires-Dist: grandalf (>=0.8,<0.9)
+Requires-Dist: langchain (>=0.3.20,<0.4.0)
+Requires-Dist: langchain-anthropic (>=0.3.10,<0.4.0)
+Requires-Dist: langchain-deepseek (>=0.1.2,<0.2.0)
+Requires-Dist: langchain-experimental (>=0.3.4,<0.4.0)
+Requires-Dist: langchain-google-genai (>=2.1.4,<3.0.0)
+Requires-Dist: langchain-openai (>=0.3.8,<0.4.0)
+Requires-Dist: langgraph (>=0.3.11,<0.4.0)
+Requires-Dist: nanoid (>=2.0.0,<3.0.0)
+Requires-Dist: pydantic (>=2.10.6,<3.0.0)
+Requires-Dist: pydantic-settings (>=2.8.1,<3.0.0)
+Requires-Dist: pyphen (>=0.17.2,<0.18.0)
+Requires-Dist: pytest (>=8.3.5,<9.0.0)
+Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: python-iso639 (>=2025.2.18,<2026.0.0)
+Requires-Dist: tenacity (>=9.1.2,<10.0.0)
+Requires-Dist: textstat (>=0.7.6,<0.8.0)
+Requires-Dist: tiktoken (>=0.9.0,<0.10.0)
+Requires-Dist: tqdm (>=4.67.1,<5.0.0)
+Description-Content-Type: text/markdown
+
+# bioguider

bioguider-0.2.3.dist-info/RECORD

@@ -0,0 +1,47 @@
+bioguider/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bioguider/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bioguider/agents/agent_task.py,sha256=SX4iLdGqQttT39qvr-RtXiSpQEzm7Z3ECVw8IGQzpDc,2828
+bioguider/agents/agent_tools.py,sha256=Q7yciRjMwW4J6V4TGZx_smaBYiV_ZtmKkjBb1ofVgM0,5898
+bioguider/agents/agent_utils.py,sha256=qngmkCiTz46PJebzWmdZLo5XWtyUDZddCQv06PDKBrw,12450
+bioguider/agents/collection_execute_step.py,sha256=6hCCP9LG5goC-EbS6Ye3wKS4vPy7p9NndMYo48Qt3RA,5515
+bioguider/agents/collection_observe_step.py,sha256=iNeV6f16Emk1LMStSR4FXBPZ6Sc0eTjwxEfmoeegV-U,4554
+bioguider/agents/collection_plan_step.py,sha256=mx-_5Y3pqKDPBaMMyFElKlpq1GWN7g03ZplnlTr9ppE,5699
+bioguider/agents/collection_task.py,sha256=9jqasC5PVZvnPzQtLGAJiYvO1M2RGWH7tqWO6KbEnl8,6663
+bioguider/agents/collection_task_utils.py,sha256=WRzzpMV6r8aY0FlX_zroHbLDXyrmvS48OSiBr_fIq2Q,3677
+bioguider/agents/common_agent.py,sha256=eGs8m8bjO0dmW6lDIen7DQNdWdHD7j8Udf3XhL1k6vI,5242
+bioguider/agents/common_agent_2step.py,sha256=wIg9m9-8tq0AYrG2quuI1ZYg82Q54MHtTQLG4pqN8y4,4596
+bioguider/agents/common_step.py,sha256=GdOCbmj1pwh4etg-futVFYVDQuoUG89DnIrw-B6QbzM,2594
+bioguider/agents/dockergeneration_execute_step.py,sha256=F92jDlkc6KjAvTkX7q1FsCYP8J15SCaNgmwh3YPqfDo,6500
+bioguider/agents/dockergeneration_observe_step.py,sha256=gVCsr0EiKCgYMRQvev_LWBf78yHzLxIltPVIgRmdS3o,6062
+bioguider/agents/dockergeneration_plan_step.py,sha256=v0X95Lzj5kjfqcOch6IOMcuOfsRBkgJjsYDlxMpblLI,7204
+bioguider/agents/dockergeneration_task.py,sha256=ezsweVHJsFpOyOI6rYMt1DZ3PE19dcq4J3Lm-d0IA8M,6220
+bioguider/agents/dockergeneration_task_utils.py,sha256=v7emqrJlVW-A5ZdLmPSdiaMSKCR8uzy9UYzx_1cgzyo,9041
+bioguider/agents/evaluation_task.py,sha256=iEa47N1iL-MgLKNZfMzRjjMcg2rEqSis4FeXaEGYLJQ,10928
+bioguider/agents/identification_execute_step.py,sha256=_9x_KITVtNJjQlgjfq-LazoUl46Tctaj_W_AVxz5q-w,5488
+bioguider/agents/identification_observe_step.py,sha256=B5E61luYteyKOaMZsgjxI-xuNijPfAjNpNBWL5DyTHc,3636
+bioguider/agents/identification_plan_step.py,sha256=p-a3vc0qhifJCM0cerFVAtYuYSvqImzqCsQofFaQRrs,5193
+bioguider/agents/identification_task.py,sha256=-4bnw39OSkhu8RkDVQPRpmu0g8K79dji3HXTybch5As,8329
+bioguider/agents/identification_task_utils.py,sha256=5gevknha9hJiiQN5L7Yp9-pyhAlbR_j31aGRK5j0D_w,522
+bioguider/agents/peo_common_step.py,sha256=iw2c1h7X11WJzSE2tSRg0UAoXH0QOlQDxW9CCzSVMOY,2677
+bioguider/agents/prompt_utils.py,sha256=KBNWsUJMjZAczD_y7nFMnjfJv4dVBPI3cAlQDMbFHec,12379
+bioguider/agents/python_ast_repl_tool.py,sha256=o7-4P1h8jS8ikhGSA4CI_OWQ2a0Eg5tEdmuAp_qrO-0,2519
+bioguider/agents/rag_collection_task.py,sha256=r_jPAMjQcC7dIydKxX77UuMqjJ3MiVKswNZ-yNw7yx8,5199
+bioguider/conversation.py,sha256=DIvk_d7pz_guuORByK1eaaF09FAK-8shcNTrbSUHz9Y,1779
+bioguider/database/summarized_file_db.py,sha256=9Iyin5BChlFjDJlFamTwmzkYZvO3BzFu7M8AbikyPXw,4441
+bioguider/managers/evaluation_manager.py,sha256=EtVSTP75mtlvXDcXKMedsqlwUZEkxaD9MBwHJQfpmr4,3920
+bioguider/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bioguider/rag/config.py,sha256=5g4IqTzgyfZfax9Af9CTkXShgItPOt4_9TEMSekCPik,4602
+bioguider/rag/data_pipeline.py,sha256=rG3iSxWlIZzQ5ml3E2Zo7UJEnlVeeneAm_kSCsngUhw,27126
+bioguider/rag/embedder.py,sha256=jofR8hOj3Aj2IyBQ9y6FeAc84tgq5agbIfCGyFxYpJ8,650
+bioguider/rag/rag.py,sha256=2G2b7JIDsjrR74lnkIFyEuMPF14kn6B-WhphZkUxd3c,4481
+bioguider/settings.py,sha256=BD_iz9aYarxmWUl0XaKl4-D4oTXMhFzljsXLNn2phis,3143
+bioguider/utils/constants.py,sha256=_xMAhwE3py2RR0pIimnb2qfucXdnTj4ZNeKGACouh2w,932
+bioguider/utils/default.gitignore,sha256=XjPdyO2KV8z8iyuqluaNR_70tBQftMpyKL8HboVNyeI,1605
+bioguider/utils/file_utils.py,sha256=R68ayY1flc2Mbl7yMkp_39AUzw5_8iPF5Ow3YVQaZdY,3610
+bioguider/utils/gitignore_checker.py,sha256=pOYUwsS9D5014LxcZb0cj3s2CAYaD2uF_pYJpaNKcho,6532
+bioguider/utils/pyphen_utils.py,sha256=cdZc3qphkvMDeL5NiZ8Xou13M_uVNP7ifJ-FwxO-0BE,2680
+bioguider/utils/utils.py,sha256=YP3HXgU_rvYDWkEcTzWGiYZw-mlfVrqGhUGSc0_4Pms,900
+bioguider-0.2.3.dist-info/LICENSE,sha256=qzkvZcKwwA5DuSuhXMOm2LcO6BdEr4V7jwFZVL2-jL4,1065
+bioguider-0.2.3.dist-info/METADATA,sha256=_Vaa_hK-a2Y9bI07jzhC8UW16TLjMlwLjqXVfwOSJzQ,1823
+bioguider-0.2.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+bioguider-0.2.3.dist-info/RECORD,,

bioguider-0.2.3.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.1.3
+Root-Is-Purelib: true
+Tag: py3-none-any