Add documentation to PdfMinerState

src/ocrmypdf/pdfinfo/layout.py

@@ -322,7 +322,19 @@ def get_page_analysis(
 
 
 class PdfMinerState:
-    def __init__(self, infile: Path, pscript5_mode: bool):
+    """Provide a context manager for using pdfminer.six.
+
+    This ensures that the file is closed. It also provides a cache of pages
+    from the PDF so that they can be reused if needed, to improve performance.
+    """
+
+    def __init__(self, infile: Path, pscript5_mode: bool) -> None:
+        """Initialize the context manager.
+
+        Args:
+            infile: The path to the PDF file to be analyzed.
+            pscript5_mode: Whether the PDF was generated by PScript5.dll.
+        """
         self.infile = infile
         self.rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
         self.disable_boxes_flow = None
@@ -331,15 +343,18 @@ def __init__(self, infile: Path, pscript5_mode: bool):
         self.file = None
 
     def __enter__(self):
+        """Enter the context manager."""
         self.file = Path(self.infile).open('rb')
         return self
 
     def __exit__(self, exc_type, exc_value, traceback):
+        """Exit the context manager."""
         if self.file:
             self.file.close()
         return True
 
     def _load_page_cache(self):
+        """Load the page cache."""
         try:
             self.page_cache = list(PDFPage.get_pages(self.file))
             if not self.page_cache:
@@ -355,6 +370,7 @@ def _load_page_cache(self):
             raise EncryptedPdfError() from e
 
     def get_page_analysis(self, pageno: int):
+        """Get the page analysis for a given page."""
         if not self.page_cache:
             self._load_page_cache()
         page = self.page_cache[pageno]