pyformatjson 0.2.6__tar.gz → 0.3.0__tar.gz

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/.github/workflows/release.yml

@@ -41,6 +41,6 @@ jobs:
         uses: softprops/action-gh-release@v2
         with:
           body_path: CHANGELOG.md
-          # generate_release_notes: true
+          generate_release_notes: true
         env:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}

pyformatjson-0.3.0/.python-version

@@ -0,0 +1 @@
+3.12

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyformatjson
-Version: 0.2.6
+Version: 0.3.0
 Summary: pyformatjson
 Project-URL: Homepage, https://github.com/Easy-PhD/pyformatjson
 Project-URL: Repository, https://github.com/Easy-PhD/pyformatjson
@@ -26,7 +26,7 @@ Requires-Dist: func-timeout>=4.3.5
 Requires-Dist: lxml>=6.0.2
 Requires-Dist: playwright>=1.55.0
 Requires-Dist: psutil>=7.1.2
-Requires-Dist: pyadvtools>=0.3.8
+Requires-Dist: pyadvtools>=0.3.10
 Requires-Dist: requests>=2.32.5
 Requires-Dist: selenium>=4.38.0
 Description-Content-Type: text/markdown

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/docs/requirements.txt

@@ -1,3 +1,4 @@
+ruff>=0.14.3
 mkdocs>=1.6.1
 mkdocs-autorefs>=1.4.3
 mkdocs-material>=9.6.21

pyformatjson-0.2.6/pyformatjson.sublime-project → pyformatjson-0.3.0/main.sublime-project

@@ -8,6 +8,15 @@
             "target": "terminus_exec",
             "cancel": "terminus_cancel_build",
             "shell_cmd": "\".venv/bin/python3\" -u \"$file\"",
+            "windows": {
+                "shell_cmd": "\".venv\\Scripts\\python.exe\" -u \"$file\"",
+            },
+            "osx": {
+                "shell_cmd": "\".venv/bin/python3\" -u \"$file\"",
+            },
+            "linux": {
+                "shell_cmd": "\".venv/bin/python3\" -u \"$file\"",
+            },
             "env": {
                 "PYTHONIOENCODING": "utf-8",
                 "PYTHONPATH": ".",
@@ -17,8 +26,6 @@
     ],
     "settings": {},
     "folders": [
-        {
-            "path": ".",
-        },
+        { "path": ".", },
     ],
 }

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/pyformatjson/core/_base.py

@@ -69,8 +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":

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/pyformatjson/core/update_json.py

@@ -12,7 +12,7 @@ def load_json_data(path_json: str, filename: str) -> dict:
         if not os.path.exists(file_path):
             return {}
 
-        with open(file_path, encoding="utf-8") as file:
+        with open(file_path, encoding="utf-8", newline="\n") as file:
             return json.load(file)
 
     except Exception as e:
@@ -63,12 +63,45 @@ def update_json_file(full_json_cj: str, conferences_or_journals: str) -> dict[st
 
     # Save updated JSON
     if flag and json_dict:
-        with open(full_json_cj, "w", encoding="utf-8") as f:
+        json_dict = add_multiple_add(json_dict, conferences_or_journals)
+
+        with open(full_json_cj, "w", encoding="utf-8", newline="\n") as f:
             f.write(json.dumps(json_dict, indent=4, sort_keys=True, ensure_ascii=True))
 
     return json_dict
 
 
+def add_multiple_add(json_dict, conferences_or_journals):
+    for pub in json_dict:
+        for key in json_dict[pub][conferences_or_journals]:
+            names_abbr = json_dict[pub][conferences_or_journals][key].get("names_abbr", [])
+            names_full = json_dict[pub][conferences_or_journals][key].get("names_full", [])
+
+            names_abbr_, names_full_ = [], []
+            for abbr, full in zip(names_abbr, names_full, strict=True):
+                names_abbr_.append(abbr)
+                names_full_.append(full)
+
+                full = full.encode('unicode_escape').decode()
+                if "&" in full and r"\\&" not in full and r"\\\\&" not in full:
+                    full_1 = re.sub("&", r"\\&", full)
+                    full_2 = re.sub("&", r"\\\\&", full)
+                    if full_1 not in names_full:
+                        breakpoint()
+                        names_abbr_.append(abbr)
+                        names_full_.append(full_1)
+
+                    if full_2 not in names_full:
+                        breakpoint()
+                        names_abbr_.append(abbr)
+                        names_full_.append(full_2)
+
+            json_dict[pub][conferences_or_journals][key]["names_abbr"] = names_abbr_
+            json_dict[pub][conferences_or_journals][key]["names_full"] = names_full_
+
+    return json_dict
+
+
 def generate_standard_form(json_dict: dict[str, Any], conferences_or_journals: str):
     # Check for duplicate abbreviations in the data.
     abbr_list = []
@@ -169,8 +202,7 @@ class CheckAcronymAbbrAndFullDict:
             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, [])
+                    item.lower().replace("(", "").replace(")", "") for item in data[main_acronym].get(key_type, [])
                 ]
 
                 # Create exact match patterns
@@ -179,17 +211,13 @@ class CheckAcronymAbbrAndFullDict:
                 matches_found = []
 
                 # Compare with other acronyms
-                for other_acronym in acronyms[i + 1:]:
+                for other_acronym in acronyms[i + 1 :]:
                     other_items = [
-                        item.lower().replace("(", "").replace(")", "")
-                        for item in data[other_acronym].get(key_type, [])
+                        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)
-                    ]
+                    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])

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/pyformatjson/tools/generate_dict.py

@@ -635,7 +635,7 @@ class GenerateDataDict:
         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, encoding="utf-8") as file:
+        with open(full_readme, encoding="utf-8", newline="\n") as file:
             data_list = file.readlines()
         for line in data_list:
             if mch := regex.search(line):

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/pyformatjson/tools/write_dict.py

@@ -8,9 +8,9 @@ from .generate_dict import conference_journal_header
 def create_safe_filename(text: str) -> str:
     """Create a safe filename across all platforms."""
     # Remove or replace invalid characters
-    safe_text = re.sub(r'[<>:"/\\|?*]', '_', text)
+    safe_text = re.sub(r'[<>:"/\\|?*]', "_", text)
     # Remove leading/trailing spaces and dots
-    safe_text = safe_text.strip(' .')
+    safe_text = safe_text.strip(" .")
     # Ensure it's not empty
     return safe_text if safe_text else "unnamed"
 
@@ -135,7 +135,7 @@ class WriteDataToMd:
 
         # Write to file
         output_file = os.path.join(self.path_output, f"Introductions_{self.cj.title()}.md")
-        with open(output_file, "w", encoding="utf-8") as f:
+        with open(output_file, "w", encoding="utf-8", newline="\n") as f:
             f.writelines(data_list)
 
     # --------- --------- --------- --------- --------- --------- --------- --------- --------- #
@@ -208,7 +208,10 @@ class WriteDataToMd:
         # Write to file
         category_postfix = f"_{keywords_category_name.title()}" if keywords_category_name else ""
         with open(
-            os.path.join(self.path_output, f"Categories_{self.cj.title()}{category_postfix}.md"), "w", encoding="utf-8"
+            os.path.join(self.path_output, f"Categories_{self.cj.title()}{category_postfix}.md"),
+            "w",
+            encoding="utf-8",
+            newline="\n",
         ) as f:
             f.writelines(data_list)
 
@@ -249,7 +252,7 @@ class WriteDataToMd:
             path_key = standardize_path(os.path.join(self.path_output, f"Categories_{self.cj.title()}"))
             # Create safe filename by replacing invalid characters
             safe_keyword = create_safe_filename(keyword).replace(" ", "_")
-            with open(os.path.join(path_key, f"{safe_keyword}.md"), "w", encoding="utf-8") as f:
+            with open(os.path.join(path_key, f"{safe_keyword}.md"), "w", encoding="utf-8", newline="\n") as f:
                 f.writelines(data_list)
 
         return None
@@ -295,7 +298,9 @@ class WriteDataToMd:
             idx += 1
 
         # Write to file
-        with open(os.path.join(self.path_output, f"Publishers_{self.cj.title()}.md"), "w", encoding="utf-8") as f:
+        with open(
+            os.path.join(self.path_output, f"Publishers_{self.cj.title()}.md"), "w", encoding="utf-8", newline="\n"
+        ) as f:
             f.writelines(data_list_pub)
         return None
 
@@ -359,7 +364,7 @@ class WriteDataToMd:
 
             # Write publisher-specific file
             path_pub = standardize_path(os.path.join(self.path_output, f"Publishers_{self.cj.title()}"))
-            with open(os.path.join(path_pub, f"{pub}.md"), "w", encoding="utf-8") as f:
+            with open(os.path.join(path_pub, f"{pub}.md"), "w", encoding="utf-8", newline="\n") as f:
                 f.writelines(data_list)
 
         return None
@@ -403,7 +408,10 @@ class WriteDataToMd:
         # Write to file
         category_postfix = f"_{keywords_category_name.title()}" if keywords_category_name else ""
         with open(
-            os.path.join(self.path_output, f"Statistics_{self.cj.title()}{category_postfix}.md"), "w", encoding="utf-8"
+            os.path.join(self.path_output, f"Statistics_{self.cj.title()}{category_postfix}.md"),
+            "w",
+            encoding="utf-8",
+            newline="\n",
         ) as f:
             f.writelines(data_list)
         return None
@@ -449,7 +457,7 @@ class WriteDataToMd:
             path_pub = standardize_path(os.path.join(self.path_output, f"Statistics_{self.cj.title()}"))
             # Create safe filename by replacing invalid characters
             safe_keyword = create_safe_filename(keyword).replace(" ", "_")
-            with open(os.path.join(path_pub, f"{safe_keyword}.md"), "w", encoding="utf-8") as f:
+            with open(os.path.join(path_pub, f"{safe_keyword}.md"), "w", encoding="utf-8", newline="\n") as f:
                 f.writelines(data_list)
 
         return None

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pyformatjson"
-version = "0.2.6"
+version = "0.3.0"
 description = "pyformatjson"
 license = "GPL-3.0-or-later"
 license-files = ["LICENSE"]
@@ -28,7 +28,7 @@ dependencies = [
     "lxml>=6.0.2",
     "playwright>=1.55.0",
     "psutil>=7.1.2",
-    "pyadvtools>=0.3.8",
+    "pyadvtools>=0.3.10",
     "requests>=2.32.5",
     "selenium>=4.38.0",
 ]

{pyformatjson-0.2.6 → pyformatjson-0.3.0}/scripts/generate_docs.py

@@ -35,13 +35,14 @@ class DocGenerator:
     def get_module_info(self, module_path: Path) -> dict[str, Any]:
         # Calculate relative import path
         relative_path = module_path.relative_to(self.source_dir)
-        module_name = str(relative_path).replace("/", ".").replace("\\", ".").replace(".py", "")
+        module_name = str(relative_path).replace("/", ".").replace("\\", ".")
+        module_name = module_name[:-3]  # replace(".py", "")
 
         return {
             "path": module_path,
             "name": module_name,
             "import_path": f"{self.package_name}.{module_name}",
-            "doc_path": self.api_dir / f"{module_name}.md"
+            "doc_path": self.api_dir / f"{module_name}.md",
         }
 
     def generate_module_doc(self, module_info: dict[str, Any]) -> str:
@@ -58,7 +59,7 @@ class DocGenerator:
             "      heading_level: 2",
             "      show_source: true",
             "      show_category_heading: true",
-            ""
+            "",
         ]
 
         return "\n".join(content)
@@ -73,7 +74,7 @@ class DocGenerator:
             f"This is the complete API reference documentation for the {self.package_name} library.",
             "",
             "## Module List",
-            ""
+            "",
         ]
 
         # Group modules by directory
@@ -104,7 +105,7 @@ class DocGenerator:
         # Ensure directory exists
         filepath.parent.mkdir(parents=True, exist_ok=True)
 
-        with open(filepath, "w", encoding="utf-8") as f:
+        with open(filepath, "w", encoding="utf-8", newline="\n") as f:
             f.write(content)
 
         print(f"✓ Generated documentation: {filepath}")

pyformatjson-0.3.0/tests/test_main.py

@@ -0,0 +1,18 @@
+import os
+
+from pyformatjson.main import main_generate_md_files
+
+if __name__ == "__main__":
+    full_json_c = os.getenv("FULL_JSON_C", "")
+    full_json_j = os.getenv("FULL_JSON_J", "")
+    full_json_k = os.getenv("FULL_JSON_K", "")
+    path_spidered_bibs = os.getenv("PATH_SPIDERED_BIBS", "")
+    path_output = os.path.join(os.getenv("PATH_AILINKS", ""), "docs", "data")
+
+    main_generate_md_files(full_json_c, full_json_j, full_json_k, path_output, path_spidered_bibs)
+    main_generate_md_files(
+        full_json_c, full_json_j, full_json_k, path_output, path_spidered_bibs, keywords_category_name="S"
+    )
+    main_generate_md_files(
+        full_json_c, full_json_j, full_json_k, path_output, path_spidered_bibs, keywords_category_name="Y"
+    )