pyformatjson 0.2.4__tar.gz → 0.2.5__tar.gz

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyformatjson
-Version: 0.2.4
+Version: 0.2.5
 Summary: pyformatjson
 License: GPL-3.0-or-later
 License-File: LICENSE

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyformatjson/core/_base.py

@@ -1,11 +1,8 @@
-# coding=utf-8
-
 import os
 import re
-from typing import List
 
 
-def split_text_by_length(text, max_length=120) -> List[str]:
+def split_text_by_length(text, max_length=120) -> list[str]:
     """Split text into lines of specified maximum length.
 
     This function breaks long text into multiple lines, ensuring each line
@@ -17,7 +14,7 @@ def split_text_by_length(text, max_length=120) -> List[str]:
         max_length (int, optional): Maximum length for each line. Defaults to 120.
 
     Returns:
-        List[str]: A list of text lines, each not exceeding max_length characters.
+        list[str]: A list of text lines, each not exceeding max_length characters.
 
     Example:
         >>> split_text_by_length("This is a very long text that needs to be split", 20)
@@ -44,8 +41,8 @@ def split_text_by_length(text, max_length=120) -> List[str]:
     return new_lines
 
 
-def split_data_list(split_pattern: str, data_list: List[str], last_next: str = "next") -> List[str]:
-    """Split data list according to the split pattern.
+def split_data_list(split_pattern: str, data_list: list[str], last_next: str = "next") -> list[str]:
+    r"""Split data list according to the split pattern.
 
     This function splits each string in the data list using the provided regex pattern
     and reconstructs the data based on the last_next parameter. The pattern must use
@@ -54,13 +51,13 @@ def split_data_list(split_pattern: str, data_list: List[str], last_next: str = "
     Args:
         split_pattern (str): Regular expression pattern for splitting. Must use capturing
             parentheses, e.g., r"(\n)" for newline splits.
-        data_list (List[str]): List of strings to be split and processed.
+        data_list (list[str]): List of strings to be split and processed.
         last_next (str, optional): Determines how to handle split parts. "next" places
             the split character at the beginning of the next part, "last" places it at
             the end of the current part. Defaults to "next".
 
     Returns:
-        List[str]: New list of processed strings with empty strings filtered out.
+        list[str]: New list of processed strings with empty strings filtered out.
 
     Raises:
         re.error: If the split_pattern is not a valid regular expression.
@@ -72,8 +69,8 @@ def split_data_list(split_pattern: str, data_list: List[str], last_next: str = "
     new_data_list = []
     for line in data_list:
         split_list = re.split(split_pattern, line)
-        list_one = split_list[0 : len(split_list) : 2]
-        list_two = split_list[1 : len(split_list) : 2]
+        list_one = split_list[0: len(split_list): 2]
+        list_two = split_list[1: len(split_list): 2]
 
         temp = []
         if last_next == "next":
@@ -109,7 +106,7 @@ def standardize_path(path_input: str) -> str:
     return path_input
 
 
-def sort_strings_with_embedded_numbers(s: str) -> List[str]:
+def sort_strings_with_embedded_numbers(s: str) -> list[str]:
     """Split string into pieces for natural sorting with embedded numbers.
 
     This function splits a string into pieces where numbers are converted to integers
@@ -119,7 +116,7 @@ def sort_strings_with_embedded_numbers(s: str) -> List[str]:
         s (str): The string to be split into sortable pieces.
 
     Returns:
-        List[str]: List of string pieces with numbers converted to integers.
+        list[str]: List of string pieces with numbers converted to integers.
 
     Example:
         >>> sort_strings_with_embedded_numbers("item10")
@@ -131,18 +128,18 @@ def sort_strings_with_embedded_numbers(s: str) -> List[str]:
     return pieces
 
 
-def sort_int_str(str_int: List[str], reverse: bool = False) -> List[str]:
+def sort_int_str(str_int: list[str], reverse: bool = False) -> list[str]:
     """Sort list of strings with embedded numbers naturally.
 
     This function sorts a list of strings using natural sorting that handles
     embedded numbers correctly (e.g., "item2" comes before "item10").
 
     Args:
-        str_int (List[str]): List of strings to be sorted.
+        str_int (list[str]): List of strings to be sorted.
         reverse (bool, optional): If True, sorts in descending order. Defaults to False.
 
     Returns:
-        List[str]: Sorted list of strings.
+        list[str]: Sorted list of strings.
 
     Example:
         >>> sort_int_str(["item10", "item2", "item1"])
@@ -151,7 +148,7 @@ def sort_int_str(str_int: List[str], reverse: bool = False) -> List[str]:
     return sorted(str_int, key=sort_strings_with_embedded_numbers, reverse=reverse)
 
 
-class IterateSortDict(object):
+class IterateSortDict:
     """A class for recursively sorting dictionary keys with natural sorting.
 
     This class provides methods to sort dictionary keys recursively, handling

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyformatjson/core/update_json.py

@@ -1,20 +1,18 @@
-# coding=utf-8
-
 import json
 import os
 import re
-from typing import Any, Dict, List, Tuple
+from typing import Any
 
 from ._base import split_data_list, split_text_by_length
 
 
-def load_json_data(path_json: str, filename: str) -> Dict:
+def load_json_data(path_json: str, filename: str) -> dict:
     try:
         file_path = os.path.join(path_json, filename)
         if not os.path.exists(file_path):
             return {}
 
-        with open(file_path, "r", encoding="utf-8") as file:
+        with open(file_path, encoding="utf-8") as file:
             return json.load(file)
 
     except Exception as e:
@@ -22,7 +20,7 @@ def load_json_data(path_json: str, filename: str) -> Dict:
         return {}
 
 
-def update_json_file(full_json_cj: str, conferences_or_journals: str) -> Dict[str, Any]:
+def update_json_file(full_json_cj: str, conferences_or_journals: str) -> dict[str, Any]:
     """Update and format JSON file containing conference/journal data.
 
     This function loads JSON data, processes and formats text fields by splitting
@@ -34,7 +32,7 @@ def update_json_file(full_json_cj: str, conferences_or_journals: str) -> Dict[st
         conferences_or_journals (str): Type of publication ('conferences' or 'journals').
 
     Returns:
-        Dict[str, Any]: Processed JSON data dictionary.
+        dict[str, Any]: Processed JSON data dictionary.
     """
     # Load Json Data
     json_dict = load_json_data(os.path.dirname(full_json_cj), os.path.basename(full_json_cj))
@@ -71,7 +69,7 @@ def update_json_file(full_json_cj: str, conferences_or_journals: str) -> Dict[st
     return json_dict
 
 
-def generate_standard_form(json_dict: Dict[str, Any], conferences_or_journals: str):
+def generate_standard_form(json_dict: dict[str, Any], conferences_or_journals: str):
     # Check for duplicate abbreviations in the data.
     abbr_list = []
     for pub in json_dict:
@@ -82,7 +80,7 @@ def generate_standard_form(json_dict: Dict[str, Any], conferences_or_journals: s
                 abbr_list.append(abbr)
 
     # Extract abbreviation and name data from all publications
-    abbr_dict: Dict[str, Dict[str, List[str]]] = {}
+    abbr_dict: dict[str, dict[str, list[str]]] = {}
     for pub in json_dict:
         if conferences_or_journals in json_dict[pub]:
             for abbr, v in json_dict[pub][conferences_or_journals].items():
@@ -97,7 +95,7 @@ class CheckAcronymAbbrAndFullDict:
         self.names_abbr = names_abbr
         self.names_full = names_full
 
-    def run(self, dict_data: dict[str, dict[str, list[str]]]) -> Tuple[dict[str, dict[str, list[str]]], bool]:
+    def run(self, dict_data: dict[str, dict[str, list[str]]]) -> tuple[dict[str, dict[str, list[str]]], bool]:
         # Check if each acronym has equal number of abbreviations and full forms
         dict_data, length_check = self._validate_lengths(dict_data)
 
@@ -137,7 +135,7 @@ class CheckAcronymAbbrAndFullDict:
             has_duplicate = False
 
             # Check for duplicate abbreviations
-            abbrs_lower = set([abbr.lower() for abbr in values.get(self.names_abbr, [])])
+            abbrs_lower = {abbr.lower() for abbr in values.get(self.names_abbr, [])}
             for abbr in abbrs_lower:
                 if abbr in seen_abbrs:
                     print(f"Duplicate abbreviation '{abbr}' found in '{acronym}'")
@@ -146,7 +144,7 @@ class CheckAcronymAbbrAndFullDict:
                     seen_abbrs.add(abbr)
 
             # Check for duplicate full forms
-            fulls_lower = set([full.lower() for full in values.get(self.names_full, [])])
+            fulls_lower = {full.lower() for full in values.get(self.names_full, [])}
             for full in fulls_lower:
                 if full in seen_fulls:
                     print(f"Duplicate full form '{full}' found in '{acronym}'")
@@ -165,40 +163,41 @@ class CheckAcronymAbbrAndFullDict:
         """Check for exact matches in abbreviations or full forms between different acronyms."""
         valid_data = {}
         no_matches = True
-        acronyms = sorted(list(data.keys()))
+        acronyms_bak = sorted(data.keys())
 
-        for i, main_acronym in enumerate(acronyms):
-            # Normalize items: lowercase and remove parentheses
-            main_items = [
-                item.lower().replace("(", "").replace(")", "")
-                for item in data[main_acronym].get(key_type, [])
-            ]
+        for acronyms in [acronyms_bak, acronyms_bak[::-1]]:
+            for i, main_acronym in enumerate(acronyms):
+                # Normalize items: lowercase and remove parentheses
+                main_items = [
+                    item.lower().replace("(", "").replace(")", "")
+                    for item in data[main_acronym].get(key_type, [])
+                ]
 
-            # Create exact match patterns
-            patterns = [re.compile(f"^{item}$") for item in main_items]
+                # Create exact match patterns
+                patterns = [re.compile(f"^{item}$") for item in main_items]
 
-            matches_found = []
+                matches_found = []
 
-            # Compare with other acronyms
-            for other_acronym in acronyms[i + 1:]:
-                other_items = [
-                    item.lower().replace("(", "").replace(")", "")
-                    for item in data[other_acronym].get(key_type, [])
-                ]
+                # Compare with other acronyms
+                for other_acronym in acronyms[i + 1:]:
+                    other_items = [
+                        item.lower().replace("(", "").replace(")", "")
+                        for item in data[other_acronym].get(key_type, [])
+                    ]
 
-                # Find matching items
-                matching_items = [
-                    item for item in other_items
-                    if any(pattern.match(item) for pattern in patterns)
-                ]
+                    # Find matching items
+                    matching_items = [
+                        item for item in other_items
+                        if any(pattern.match(item) for pattern in patterns)
+                    ]
 
-                if matching_items:
-                    matches_found.append([main_acronym, other_acronym, matching_items])
+                    if matching_items:
+                        matches_found.append([main_acronym, other_acronym, matching_items])
 
-            if matches_found:
-                no_matches = False
-                print(f"Found matches in {key_type}: {matches_found}")
-            else:
-                valid_data[main_acronym] = data[main_acronym]
+                if matches_found:
+                    no_matches = False
+                    print(f"Found matches in {key_type}: {matches_found}")
+                else:
+                    valid_data[main_acronym] = data[main_acronym]
 
         return valid_data, no_matches

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyformatjson/main.py

@@ -1,7 +1,4 @@
-# coding=utf-8
-
 import os
-from typing import Optional
 
 from .core._base import standardize_path
 from .core.update_json import load_json_data, update_json_file
@@ -14,7 +11,7 @@ def main_generate_md_files(
     full_json_j: str,
     full_json_k: str,
     path_output: str,
-    path_spidered_bibs: Optional[str] = None,
+    path_spidered_bibs: str | None = None,
     keywords_category_name: str = "",
     for_vue: bool = True,
 ) -> None:
@@ -70,7 +67,7 @@ def main_generate_md_files(
         keywords_list, keywords_category_name = [], ""
 
     # Process both conferences and journals
-    for cj, ia in zip(["conferences", "journals"], ["inproceedings", "article"]):
+    for cj, ia in zip(["conferences", "journals"], ["inproceedings", "article"], strict=True):
         # Update JSON data
         json_dict = {}
         if cj == "conferences":

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyformatjson/tools/generate_dict.py

@@ -1,9 +1,6 @@
-# coding=utf-8
-
 import os
 import re
 from datetime import datetime
-from typing import Optional
 
 
 def conference_journal_header():
@@ -35,7 +32,7 @@ def conference_journal_header():
     return conference_header, journal_header
 
 
-class GenerateDataDict(object):
+class GenerateDataDict:
     """Generate data dictionaries from JSON input for conferences and journals.
 
     This class processes JSON data containing conference or journal information
@@ -65,7 +62,7 @@ class GenerateDataDict(object):
         inproceedings_or_article: str,
         json_dict: dict,
         for_vue: bool = True,
-        path_spidered_conferences_or_journals: Optional[str] = None,
+        path_spidered_conferences_or_journals: str | None = None,
     ) -> None:
         """Initialize the GenerateDataDict instance.
 
@@ -294,7 +291,7 @@ class GenerateDataDict(object):
             key (str): Key to extract text content from.
 
         Returns:
-            List[str]: List of non-empty text content.
+            list[str]: List of non-empty text content.
         """
         return [text for text in abbr_dict.get(key, []) if text.strip()]
 
@@ -328,7 +325,7 @@ class GenerateDataDict(object):
         cleaned_keywords = {}
         for category, words in keywords_dict.items():
             if category.strip():
-                sorted_words = sorted(set([word.strip() for word in words if word.strip()]))
+                sorted_words = sorted({word.strip() for word in words if word.strip()})
                 cleaned_keywords[category.strip()] = sorted_words
 
         # Flatten keywords and remove duplicates
@@ -395,8 +392,7 @@ class GenerateDataDict(object):
     def _generate_for_conference(
         self, publisher_url, full_name, abbr_name, url_home, url_about, period, top, keywords, abbr, abbr_dict
     ):
-        """
-        Generate a markdown table row for conference information.
+        """Generate a markdown table row for conference information.
 
         Args:
             publisher_url: URL of the publisher
@@ -528,8 +524,7 @@ class GenerateDataDict(object):
     def _generate_for_journal(
         self, publisher_url, full_name, abbr_name, url_home, url_about, period, top, keywords, abbr, abbr_dict
     ):
-        """
-        Generate a markdown table row for journal information.
+        r"""Generate a markdown table row for journal information.
 
         Args:
             publisher_url: URL of the publisher
@@ -586,7 +581,7 @@ class GenerateDataDict(object):
             inproceedings_or_article (str): Publication type.
 
         Returns:
-            List[str]: Mermaid chart configuration lines, or empty list if no data found.
+            list[str]: Mermaid chart configuration lines, or empty list if no data found.
         """
         path_spidered_cj = self.path_spidered_cj if self.path_spidered_cj else ""
         path_readme = os.path.join(path_spidered_cj, publisher, abbr, inproceedings_or_article)
@@ -597,7 +592,7 @@ class GenerateDataDict(object):
         mermaid, data_dict = [], {}
         # |AAAI|1980|95|Proceedings of the First National Conference on Artificial Intelligence|
         regex = re.compile(r"\|.*\|([0-9]+)\|([0-9]+)\|.*\|")
-        with open(full_readme, "r", encoding="utf-8") as file:
+        with open(full_readme, encoding="utf-8") as file:
             data_list = file.readlines()
         for line in data_list:
             if mch := regex.search(line):

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyformatjson/tools/write_dict.py

@@ -1,8 +1,5 @@
-# coding=utf-8
-
 import os
 import re
-from typing import List
 
 from ..core._base import standardize_path
 from .generate_dict import conference_journal_header
@@ -42,7 +39,7 @@ def conference_journal_informations():
     return conference_inf, journal_inf
 
 
-class WriteDataToMd(object):
+class WriteDataToMd:
     """Class to write publication data to Markdown files.
 
     This class provides methods to generate various markdown documentation files
@@ -142,7 +139,7 @@ class WriteDataToMd(object):
             f.writelines(data_list)
 
     # --------- --------- --------- --------- --------- --------- --------- --------- --------- #
-    def _default_or_customized_keywords(self, keywords_category_name: str, keywords_list: List[str]):
+    def _default_or_customized_keywords(self, keywords_category_name: str, keywords_list: list[str]):
         """Get default or customized keywords based on category and provided list.
 
         This method returns either a filtered list of keywords based on the provided
@@ -150,10 +147,10 @@ class WriteDataToMd(object):
 
         Args:
             keywords_category_name (str): The category name for keywords filtering.
-            keywords_list (List[str]): List of keywords to filter by.
+            keywords_list (list[str]): List of keywords to filter by.
 
         Returns:
-            List[str]: List of keywords to use for processing.
+            list[str]: List of keywords to use for processing.
 
         Example:
             >>> writer._default_or_customized_keywords("ai", ["machine learning", "deep learning"])
@@ -173,7 +170,7 @@ class WriteDataToMd(object):
             return sorted(keywords)
 
     # --------- --------- --------- --------- --------- --------- --------- --------- --------- #
-    def save_categories(self, keywords_category_name: str, keywords_list: List[str]) -> None:
+    def save_categories(self, keywords_category_name: str, keywords_list: list[str]) -> None:
         """Save publications categorized by keywords.
 
         This method generates markdown files organizing publications by their
@@ -181,7 +178,7 @@ class WriteDataToMd(object):
 
         Args:
             keywords_category_name (str): The category name for keywords filtering.
-            keywords_list (List[str]): List of keywords to include in the output.
+            keywords_list (list[str]): List of keywords to include in the output.
 
         Returns:
             None: This method does not return a value.
@@ -368,7 +365,7 @@ class WriteDataToMd(object):
         return None
 
     # --------- --------- --------- --------- --------- --------- --------- --------- --------- #
-    def save_statistics(self, keywords_category_name: str, keywords_list: List[str]) -> None:
+    def save_statistics(self, keywords_category_name: str, keywords_list: list[str]) -> None:
         """Save statistics overview file for keywords.
 
         This method generates a markdown file containing statistics overview
@@ -376,7 +373,7 @@ class WriteDataToMd(object):
 
         Args:
             keywords_category_name (str): The category name for keywords filtering.
-            keywords_list (List[str]): List of keywords to include in the output.
+            keywords_list (list[str]): List of keywords to include in the output.
 
         Returns:
             None: This method does not return a value.

{pyformatjson-0.2.4 → pyformatjson-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pyformatjson"
-version = "0.2.4"
+version = "0.2.5"
 description = "pyformatjson"
 license = "GPL-3.0-or-later"
 authors = ["NextAI <nextartifintell@gmail.com>"]
@@ -23,8 +23,6 @@ sphinx-copybutton = "^0.5.2"
 [tool.pyright]
 venvPath = "."
 venv = ".venv"
-reportOptionalSubscript = "none"  # "none", "information", "error"
-reportIncompatibleMethodOverride = "none"  # "none", "information", "error"
 
 [tool.ruff]
 line-length = 120
@@ -48,6 +46,7 @@ extend-select = [
     "A",   # flake8-builtins
     "C4",  # flake8-comprehensions
     "RUF", # Ruff-specific rules
+    "BLE", # flake8-blind-except
 ]
 
 ignore = [
@@ -58,12 +57,16 @@ ignore = [
     "ANN202",  # Missing return type of private function
     "ANN204",  # Missing return type annotation for special method `__init__`
     "ANN205",  # Missing return type annotation for staticmethod
+    "D101",  # Missing docstring in public class
     "D102",  # Missing docstring in public method
     "D103",  # Missing docstring in public function
+    "D104",  # Missing docstring in public package
     "D107",  # Missing docstring in `__init__`
+    "D100",  # Missing docstring in public module
     "D204",  # 1 blank line required after class docstring
     "D417",  # Missing argument description in the docstring
     "RUF002",  # Docstring contains ambiguous `–` (EN-DASH)
+    "RUF022",  # `__all__` is not sorted
 ]
 
 [tool.ruff.lint.pydocstyle]