pdflinkcheck 1.1.73__py3-none-any.whl → 1.2.29__py3-none-any.whl

pdflinkcheck/helpers.py

@@ -0,0 +1,88 @@
+# src/pdflinkcheck/helpers.py
+from __future__ import annotations
+from pprint import pprint
+from typing import Any
+
+"""
+Helper functions
+"""
+
+def debug_head(label: str, data: Any, n: int = 3):
+    """Helper to cleanly print the first N items of a list or dict."""
+    print(f"\n--- [DEBUG: {label}] ---")
+    if isinstance(data, list):
+        pprint(data[:n], indent=2, compact=True, width=100)
+    elif isinstance(data, dict):
+        # Print first N keys
+        head_dict = {k: data[k] for k in list(data.keys())[:n]}
+        pprint(head_dict, indent=2, compact=True, width=100)
+    else:
+        print(data)
+
+
+class PageRef:
+    """
+    A simple translator to handle the 0-to-1 index conversion 
+    without the 'Double Bump' risk.
+    """
+    def __init__(self, index: int):
+        self.index = index  # The 0-based physical index
+
+    @property
+    def human(self) -> int:
+        """The 1-based page number for humans."""
+        return self.index + 1
+
+    @property
+    def machine(self) -> int:
+        """Alias for index. The 0-based page number for machines."""
+        return self.index
+
+    
+    @classmethod
+    def corrected_down(cls, human_num: int) -> "PageRef":
+        """Explicitly compensates for 1-based data (e.g., PyMuPDF TOC)."""
+        return cls.from_human(human_num)
+    
+    @classmethod
+    def from_pymupdf_total_page_count(cls, total_pages: int) -> "PageRef":
+        """
+        Converts PyMuPDF's doc.page_count into a PageRef 
+        representing the final valid machine-facing index.
+        """
+        return cls.from_human(total_pages)
+    
+    @classmethod
+    def from_human(cls, human_num: int) -> "PageRef":
+        """Creates a PageRef from a 1-based human page number (e.g., from TOC)."""
+        return cls(human_num - 1)
+
+    @classmethod
+    def from_index(cls, physical_index: int) -> "PageRef":
+        """Creates a PageRef from a 0-based physical index (e.g., from links)."""
+        return cls(physical_index)
+    
+    def __int__(self):
+        return self.index
+    
+    def __str__(self):
+        return str(self.human)
+
+    def __repr__(self):
+        return f"PageRef(index={self.index}, human={self.human})"
+    
+
+"""
+### Indexing Map: Physical (0) vs. Logical (1)
+
+| **File**              | **Context**      | **Index Rule**      | **Reasoning**                                                                                          |
+| --------------------- | ---------------- | ------------------- | ------------------------------------------------------------------------------------------------------ |
+| `ffi.py` (Rust bridge)| Data Extraction  | **0-indexing only** | Rust's `pdf-extract` and `lopdf` crates are 0-indexed. Data should stay raw.                           |
+| `analysis_pypdf.py`   | Data Extraction  | **0-indexing only** | `pypdf` is 0-indexed. Your previous `+ 1` hacks have been removed.                                     |
+| `analysis_pymupdf.py` | Data Extraction  | **Mixed**           | **Internal:** 0-indexed. **TOC:** `get_toc()` is natively 1-indexed. Needs normalization.              |
+| `validate.py`         | Logic/Validation | **Mixed**           | **Logic:** Uses `START_INDEX=0` for boundary checks. **Strings:** Formats error messages as 1-indexed. |
+| `report.py`           | Output/Reporting | **Mixed**           | **Data:** Keeps dictionary values at 0. **Display:** Formats CLI tables as 1-indexed.                  |
+| `helpers.py`          | Translation      | **Mixed**           | The `PageRef` class acts as the "Border Control" between 0 and 1.                                      |
+| `__init__.py`         | API Surface      | **0-indexing only** | If exposing a library, users expect 0-indexed lists of pages/links.                                    |
+
+"""

pdflinkcheck/io.py

@@ -1,9 +1,14 @@
+#!/usr/bin/env python3 
+# SPDX-License-Identifier: MIT
 # src/pdflinkcheck/io.py
+from __future__ import annotations
 import logging
 import json
 import sys
 from pathlib import Path
 from typing import Dict, Any, Union, List, Optional
+from datetime import datetime
+import time
 
 # --- Configuration ---
 
@@ -112,13 +117,15 @@ def export_report_json(
     pdf_library: str
 ) -> Path:
     """Exports structured dictionary results to a .json file."""
+    
     base_name = Path(pdf_filename).stem
-    output_path = PDFLINKCHECK_HOME / f"{base_name}_{pdf_library}_report.json"
+    output_path = PDFLINKCHECK_HOME / f"{base_name}_{pdf_library}_{get_unique_unix_time()}_report.json"
 
+    print("For more details, explore the exported file(s).")
     try:
         with open(output_path, 'w', encoding='utf-8') as f:
             json.dump(report_data, f, indent=4)
-        print(f"\nJSON report exported: {get_friendly_path(output_path)}")
+        print(f"JSON report exported: {get_friendly_path(output_path)}")
         return output_path
     except Exception as e:
         error_logger.error(f"JSON export failed: {e}", exc_info=True)
@@ -130,35 +137,18 @@ def export_report_txt(
     pdf_library: str
 ) -> Path:
     """Exports the formatted string buffer to a .txt file."""
+    #pdf_filename = implement_non_redundant_naming(pdf_filename) 
     base_name = Path(pdf_filename).stem
-    output_path = PDFLINKCHECK_HOME / f"{base_name}_{pdf_library}_report.txt"
+    output_path = PDFLINKCHECK_HOME / f"{base_name}_{pdf_library}_{get_unique_unix_time()}_report.txt" 
 
     try:
         output_path.write_text(report_text, encoding='utf-8')
-        print(f"\nTXT report exported: {get_friendly_path(output_path)}")
+        print(f"TXT report exported: {get_friendly_path(output_path)}")
         return output_path
     except Exception as e:
         error_logger.error(f"TXT export failed: {e}", exc_info=True)
         raise RuntimeError(f"TXT export failed: {e}")
 
-def export_validation_json(
-    report_data: Dict[str, Any], 
-    pdf_filename: str, 
-    pdf_library: str
-) -> Path:
-    """Exports structured dictionary validation results to a .json file."""
-    base_name = Path(pdf_filename).stem
-    output_path = PDFLINKCHECK_HOME / f"{base_name}_{pdf_library}_validation.json"
-
-    try:
-        with open(output_path, 'w', encoding='utf-8') as f:
-            json.dump(report_data, f, indent=4)
-        print(f"\nJSON validation exported: {get_friendly_path(output_path)}")
-        return output_path
-    except Exception as e:
-        error_logger.error(f"JSON validation export failed: {e}", exc_info=True)
-        raise RuntimeError(f"JSON validation export failed: {e}")
-
 # --- helpers ---
 def get_friendly_path(full_path: str) -> str:
     p = Path(full_path).resolve()
@@ -168,6 +158,20 @@ def get_friendly_path(full_path: str) -> str:
     except ValueError:
         return str(p)
     
+def get_unique_unix_time():
+        """
+        Get the unix time for right now.
+        Purpose: When added to a filename, this ensures a unique filename, to avoid overwrites for otherwise identical filenames. 
+        Pros:
+        - cheap, easy, no reason to check for collision
+
+        Cons:
+        - Longer than YYYYMMDDalpha
+        - not human readable
+        """
+        return int(time.mktime(datetime.now().timetuple())) 
+
+    
 def get_first_pdf_in_cwd() -> Optional[str]:
     """
     Scans the current working directory (CWD) for the first file ending 
@@ -210,4 +214,4 @@ def get_first_pdf_in_cwd() -> Optional[str]:
     except Exception as e:
         # Handle potential permissions errors or other issues
         print(f"Error while searching for PDF in CWD: {e}", file=sys.stderr)
-        return None
+        return None