pdfalyzer 1.17.3__tar.gz → 1.17.5__tar.gz

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # NEXT RELEASE
 
+### 1.17.5
+* Fix `PIL` lazy import
+
+### 1.17.4
+* Make `PIL` a lazy import so installs without `[extract]` extras don't fail
+
 ### 1.17.3
 * Put back `--debug` arg for CLI tools
 

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pdfalyzer
-Version: 1.17.3
+Version: 1.17.5
 Summary: Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more.
 Home-page: https://github.com/michelcrypt4d4mus/pdfalyzer
 License: GPL-3.0-or-later

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/pdfalyzer/decorators/pdf_file.py

@@ -20,6 +20,8 @@ from pdfalyzer.helpers.rich_text_helper import (attention_getting_panel, error_t
 from pdfalyzer.helpers.string_helper import exception_str
 from pdfalyzer.util.page_range import PageRange
 
+DEPENDENCY_ERROR_MSG = "Pdfalyzer is missing an optional dependency required to extract text. " + \
+                       "Try 'pip install pdfalyzer[extract]'"
 DEFAULT_PDF_ERRORS_DIR = Path.cwd().joinpath('pdf_errors')
 MIN_PDF_SIZE_TO_LOG_PROGRESS_TO_STDERR = 1024 * 1024 * 20
 
@@ -54,11 +56,11 @@ class PdfFile:
         self.file_size = self.file_path.stat().st_size
 
     def extract_page_range(
-            self,
-            page_range: PageRange,
-            destination_dir: Optional[Path] = None,
-            extra_file_suffix: Optional[str] = None
-        ) -> Path:
+        self,
+        page_range: PageRange,
+        destination_dir: Optional[Path] = None,
+        extra_file_suffix: Optional[str] = None
+    ) -> Path:
         """
         Extract a range of pages to a new PDF file.
 
@@ -86,7 +88,7 @@ class PdfFile:
 
         extracted_pages_pdf_basename = insert_suffix_before_extension(self.file_path, file_suffix).name
         extracted_pages_pdf_path = destination_dir.joinpath(extracted_pages_pdf_basename)
-        console.print(f"Extracting {page_range.file_suffix()} from '{self.file_path}' to '{extracted_pages_pdf_path}'...")
+        console.print(f"Extracting {page_range.file_suffix()} from '{self.file_path}' to '{extracted_pages_pdf_path}'")
         pdf_writer = PdfWriter()
 
         with open(self.file_path, 'rb') as source_pdf:
@@ -99,11 +101,11 @@ class PdfFile:
         return extracted_pages_pdf_path
 
     def extract_text(
-            self,
-            page_range: Optional[PageRange] = None,
-            logger: Optional[Logger] = None,
-            print_as_parsed: bool = False
-        ) -> Optional[str]:
+        self,
+        page_range: Optional[PageRange] = None,
+        logger: Optional[Logger] = None,
+        print_as_parsed: bool = False
+    ) -> Optional[str]:
         """
         Use PyPDF to extract text page by page and use Tesseract to OCR any embedded images.
 
@@ -167,7 +169,7 @@ class PdfFile:
                 if print_as_parsed:
                     print(f"{page_text}")
         except DependencyError:
-            log.error("Pdfalyzer is missing an optional dependency required to extract text. Try 'pip install pdfalyzer[extract]'")
+            log.error(DEPENDENCY_ERROR_MSG)
         except EmptyFileError:
             log.warning("Skipping empty file!")
         except PdfStreamError as e:
@@ -190,7 +192,8 @@ class PdfFile:
 
         try:
             extracted_file = self.extract_page_range(PageRange(str(page_number)), destination_dir, error_msg)
-        except Exception as e:
+        except Exception:
+            stderr_console.print_exception()
             stderr_console.print(error_text(f"Failed to extract a page for submission to PyPDF team."))
             extracted_file = None
 

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/pdfalyzer/helpers/image_helper.py

@@ -1,19 +1,19 @@
 from typing import Optional
 
-from PIL import Image
 from yaralyzer.output.rich_console import console
 
 from pdfalyzer.helpers.rich_text_helper import warning_text
 
 
-def ocr_text(image: Image.Image, image_name: str) -> Optional[str]:
+def ocr_text(image: "Image.Image", image_name: str) -> Optional[str]:
     """Use pytesseract to OCR the text in the image and return it as a string."""
     import pytesseract
+    from PIL import Image
     text = None
 
     try:
         text = pytesseract.image_to_string(image)
-    except pytesseract.pytesseract.TesseractError as e:
+    except pytesseract.pytesseract.TesseractError:
         console.print_exception()
         console.print(warning_text(f"Tesseract OCR failure '{image_name}'! No OCR text extracted..."))
     except OSError as e:

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/pdfalyzer/util/cli_tools_argument_parser.py

@@ -133,7 +133,7 @@ extract_text_parser.add_argument('--page-range', '-r',
 
 extract_text_parser.add_argument('--print-as-parsed', '-p',
                                  action='store_true',
-                                 help='print pages as they are parsed instead of waiting until document is fully parsed')
+                                 help='print pages as they are parsed instead of waiting until parsing complete')
 
 
 def parse_text_extraction_args() -> Namespace:

{pdfalyzer-1.17.3 → pdfalyzer-1.17.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdfalyzer"
-version = "1.17.3"
+version = "1.17.5"
 description = "Analyze PDFs with colors (and YARA). Visualize a PDF's inner tree-like data structure, check it against a library of YARA rules, force decodes of suspicious font binaries, and more."
 authors = ["Michel de Cryptadamus <michel@cryptadamus.com>"]
 license = "GPL-3.0-or-later"