pdfalyzer 1.17.0__tar.gz → 1.17.1__tar.gz

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/CHANGELOG.md

@@ -1,5 +1,8 @@
 # NEXT RELEASE
 
+### 1.17.1
+* Fix issue where `combine_pdfs` page ranges were indexed from 0 instead of 1
+
 # 1.17.0
 * Add `extract_pdf_pages` command line tool (imported from `clown_sort`)
 * Add `extract_text_from_pdfs` command line tool (imported from `clown_sort`)

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pdfalyzer
-Version: 1.17.0
+Version: 1.17.1
 Summary: PDF analysis tool. Scan a PDF with YARA rules, visualize its inner tree-like data structure in living color (lots of colors), force decodes of suspicious font binaries, and more.
 Home-page: https://github.com/michelcrypt4d4mus/pdfalyzer
 License: GPL-3.0-or-later
@@ -250,22 +250,16 @@ Things like, say, a hidden binary `/F` (PDF instruction meaning "URL") followed
 ## Included PDF Tools
 The Pdfalyzer comes with a few command line tools:
 
-#### `combine_pdfs`
-Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` to see the options.
+* `combine_pdfs` - Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` for more info.
+* `extract_pdf_pages` - Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` for more info.
+* `extract_text_from_pdfs` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_text_from_pdfs --help` for more info.
 
-#### `extract_pdf_pages`
-Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` to see the options.
-![](doc/extract_pages_from_pdf_help.png)
-
-#### `extract_text_from_pdfs`
-Extracts text from a PDF, including applying OCR to all embedded images. Requires that you install The Pdfalyzer's optional dependencies:
+Running `extract_text_from_pdfs` requires that you install The Pdfalyzer's optional dependencies:
 
 ```bash
 pipx install pdfalyzer[extract]
 ```
 
-Run `extract_text_from_pdfs --help` to see the options.
-
 
 ## 3rd Party PDF Tools
 ### Installing Didier Stevens's PDF Analysis Tools

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/README.md

@@ -216,22 +216,16 @@ Things like, say, a hidden binary `/F` (PDF instruction meaning "URL") followed
 ## Included PDF Tools
 The Pdfalyzer comes with a few command line tools:
 
-#### `combine_pdfs`
-Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` to see the options.
+* `combine_pdfs` - Combines multiple PDFs into a single PDF. Run `combine_pdfs --help` for more info.
+* `extract_pdf_pages` - Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` for more info.
+* `extract_text_from_pdfs` - Extracts text from a PDF, including applying OCR to all embedded images. Run `extract_text_from_pdfs --help` for more info.
 
-#### `extract_pdf_pages`
-Extracts page ranges (e.g. "10-25") from a PDF and writes them to a new PDF. Run `extract_pdf_pages --help` to see the options.
-![](doc/extract_pages_from_pdf_help.png)
-
-#### `extract_text_from_pdfs`
-Extracts text from a PDF, including applying OCR to all embedded images. Requires that you install The Pdfalyzer's optional dependencies:
+Running `extract_text_from_pdfs` requires that you install The Pdfalyzer's optional dependencies:
 
 ```bash
 pipx install pdfalyzer[extract]
 ```
 
-Run `extract_text_from_pdfs --help` to see the options.
-
 
 ## 3rd Party PDF Tools
 ### Installing Didier Stevens's PDF Analysis Tools

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/__init__.py

@@ -31,7 +31,8 @@ from pdfalyzer.helpers.rich_text_helper import print_highlighted
 from pdfalyzer.output.pdfalyzer_presenter import PdfalyzerPresenter
 from pdfalyzer.output.styles.rich_theme import PDFALYZER_THEME_DICT
 from pdfalyzer.pdfalyzer import Pdfalyzer
-from pdfalyzer.util.argument_parser import (MAX_QUALITY, ask_to_proceed, output_sections, parse_arguments,
+from pdfalyzer.util.argument_parser import ask_to_proceed, output_sections, parse_arguments
+from pdfalyzer.util.cli_tools_argument_parser import (MAX_QUALITY, ask_to_proceed,
      parse_combine_pdfs_args, parse_pdf_page_extraction_args, parse_text_extraction_args)
 from pdfalyzer.util.pdf_parser_manager import PdfParserManager
 
@@ -135,15 +136,13 @@ def combine_pdfs():
 
 
 def extract_pdf_pages() -> None:
+    """Extract a range of pages from a PDF to a new PDF."""
     args = parse_pdf_page_extraction_args()
     PdfFile(args.pdf_file).extract_page_range(args.page_range, destination_dir=args.destination_dir)
 
 
 def extract_text_from_pdfs() -> None:
-    """
-    Extract text from a single file or from all files in a given directory. Can accept
-    multiple paths as arguments on the command line.
-    """
+    """Extract text from a list of file or from all PDF files in a list of directories."""
     args: Namespace = parse_text_extraction_args()
     console.line()
 

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/decorators/pdf_file.py

@@ -34,6 +34,7 @@ class PdfFile:
         basename (str): The base name of the PDF file (with extension).
         basename_without_ext (str): The base name of the PDF file (without extension).
         extname (str): The file extension of the PDF file.
+        file_size (int): The size of the file in bytes.
     """
 
     def __init__(self, file_path: Union[str, Path]) -> None:
@@ -44,7 +45,7 @@ class PdfFile:
         self.file_path: Path = Path(file_path)
 
         if not self.file_path.exists():
-            raise FileNotFoundError(f"File '{file_path}' does not exist.")
+            raise FileNotFoundError(f"'{file_path}' is not a valid file or directory.")
 
         self.dirname = self.file_path.parent
         self.basename: str = path.basename(file_path)
@@ -71,7 +72,7 @@ class PdfFile:
         Returns:
             Path: The path to the newly created PDF file containing the extracted pages.
         """
-        destination_dir = destination_dir or self.dirname
+        destination_dir = Path(destination_dir or self.dirname)
         create_dir_if_it_does_not_exist(destination_dir)
 
         if extra_file_suffix is None:

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/detection/yaralyzer_helper.py

@@ -2,7 +2,6 @@
 Functions to help with the pre-configured YARA rules in the /yara directory.
 """
 from importlib.resources import as_file, files
-from sys import exit
 from typing import Optional, Union
 
 from yaralyzer.config import YaralyzerConfig

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/helpers/string_helper.py

@@ -3,7 +3,7 @@ Various text formatting/styling/manipulating methods.
 """
 import re
 from pprint import PrettyPrinter
-from typing import List, Pattern, Union
+from typing import List, Optional, Pattern, Union
 
 from yaralyzer.output.rich_console import console_width
 
@@ -18,16 +18,14 @@ pp = PrettyPrinter(
     sort_dicts=True)
 
 
-def generate_hyphen_line(width=None, title=None):
-    """e.g. '-----------------BEGIN-----------------'"""
-    width = width or console_width()
+def all_strings_are_same_ignoring_numbers(strings: List[str]) -> bool:
+    """Returns true if string addresses are same except for digits."""
+    return len(set([replace_digits(s) for s in strings])) == 1
 
-    if title is None:
-        return '-' * width
 
-    side_hyphens = int((width - len(title)) / 2) * '-'
-    line = side_hyphens + title + side_hyphens
-    return line if len(line) == width else line + '-'
+def bracketed(index: Union[int, str]) -> str:
+    """Surround index with [ and ]."""
+    return f"[{index}]"
 
 
 def count_pattern_matches_in_text(pattern: str, text: str) -> int:
@@ -44,9 +42,20 @@ def exception_str(e: Exception) -> str:
     return f"{type(e).__name__}: {e}"
 
 
-def root_address(_string: str) -> str:
-    """Strip the bracketed part off an address, e.g. '/Root[1]' => '/Root'."""
-    return _string.split('[')[0]
+def generate_hyphen_line(width: Optional[int] = None, title: Optional[str] = None):
+    """e.g. '-----------------BEGIN-----------------'"""
+    width = width or console_width()
+
+    if title is None:
+        return '-' * width
+
+    side_hyphens = int((width - len(title)) / 2) * '-'
+    line = side_hyphens + title + side_hyphens
+    return line if len(line) == width else line + '-'
+
+
+def has_a_common_substring(strings: List[str]) -> bool:
+    return all([is_substring_of_longer_strings_in_list(s, strings) for s in strings])
 
 
 def is_prefixed_by_any(_string: str, prefixes: List[str]) -> bool:
@@ -54,9 +63,10 @@ def is_prefixed_by_any(_string: str, prefixes: List[str]) -> bool:
     return any([_string.startswith(prefix) for prefix in prefixes])
 
 
-def bracketed(index: Union[int, str]) -> str:
-    """Surround index with [ and ]."""
-    return f"[{index}]"
+def is_substring_of_longer_strings_in_list(_string: str, strings: List[str]) -> bool:
+    """Return True if '_string' is a substring of all the 'strings' longer than '_string'."""
+    longer_strings = [s for s in strings if len(s) > len(_string)]
+    return all([_string in longer_string for longer_string in longer_strings])
 
 
 def replace_digits(string_with_digits: str) -> str:
@@ -64,18 +74,6 @@ def replace_digits(string_with_digits: str) -> str:
     return DIGIT_REGEX.sub('x', string_with_digits)
 
 
-def all_strings_are_same_ignoring_numbers(strings: List[str]) -> bool:
-    """Returns true if string addresses are same except for digits."""
-    return len(set([replace_digits(s) for s in strings])) == 1
-
-
-def is_substring_of_longer_strings_in_list(_string: str, strings: List[str]) -> bool:
-    longer_strings = [s for s in strings if len(s) > len(_string)]
-    return all([_string in longer_string for longer_string in longer_strings])
-
-
-def has_a_common_substring(strings: List[str]) -> bool:
-    return all([
-        is_substring_of_longer_strings_in_list(s, strings)
-        for s in strings
-    ])
+def root_address(_string: str) -> str:
+    """Strip the bracketed part off an address, e.g. '/Root[1]' => '/Root'."""
+    return _string.split('[')[0]

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/util/argument_parser.py

@@ -1,5 +1,5 @@
 """
-Parse command line arguments for pdfalyzer and construct the PdfalyzerConfig object.
+Parse command line arguments for `pdfalyze` and construct the `PdfalyzerConfig` object.
 """
 import sys
 from argparse import ArgumentParser, Namespace
@@ -7,23 +7,17 @@ from collections import namedtuple
 from functools import partial, update_wrapper
 from importlib.metadata import version
 from os import getcwd, path
-from pathlib import Path
 from typing import List, Optional
 
 from rich_argparse_plus import RichHelpFormatterPlus
 from rich.prompt import Confirm
 from rich.text import Text
-from yaralyzer.helpers.file_helper import files_in_dir
 from yaralyzer.util.argument_parser import export, parser, parse_arguments as parse_yaralyzer_args, source
 from yaralyzer.util.logging import log, log_and_print, log_argparse_result, log_current_config, log_invocation
 
-
 from pdfalyzer.config import ALL_STREAMS, PDFALYZER, PdfalyzerConfig
 from pdfalyzer.detection.constants.binary_regexes import QUOTE_PATTERNS
-from pdfalyzer.helpers.filesystem_helper import (do_all_files_exist, extract_page_number, file_exists, is_pdf,
-     with_pdf_extension)
 from pdfalyzer.helpers.rich_text_helper import print_highlighted
-from pdfalyzer.util.page_range import PageRangeArgumentValidator
 
 # NamedTuple to keep our argument selection orderly
 OutputSection = namedtuple('OutputSection', ['argument', 'method'])
@@ -206,142 +200,6 @@ def all_sections_chosen(args):
     return len([s for s in ALL_SECTIONS if vars(args)[s]]) == len(ALL_SECTIONS)
 
 
-#############################################################
-#  Separate arg parsers for combine_pdfs and other scripts  #
-#############################################################
-
-MAX_QUALITY = 10
-
-combine_pdfs_parser = ArgumentParser(
-    description="Combine multiple PDFs into one.",
-    epilog="If all PDFs end in a number (e.g. 'xyz_1.pdf', 'xyz_2.pdf', etc. sort the files as if those were" +
-           " page numbers prior to merging.",
-    formatter_class=RichHelpFormatterPlus)
-
-combine_pdfs_parser.add_argument('pdfs',
-                                 help='two or more PDFs to combine',
-                                 metavar='PDF_PATH',
-                                 nargs='+')
-
-combine_pdfs_parser.add_argument('-iq', '--image-quality',
-                                 help='image quality for embedded images (can compress PDF at loss of quality)',
-                                 choices=range(1, MAX_QUALITY + 1),
-                                 default=MAX_QUALITY,
-                                 type=int)
-
-combine_pdfs_parser.add_argument('-o', '--output-file',
-                                 help='path to write the combined PDFs to',
-                                 required=True)
-
-
-def parse_combine_pdfs_args() -> Namespace:
-    """Parse command line args for combine_pdfs script."""
-    args = combine_pdfs_parser.parse_args()
-    args.output_file = with_pdf_extension(args.output_file)
-    confirm_overwrite_txt = Text("Overwrite '").append(args.output_file, style='cyan').append("'?")
-    args.number_of_pdfs = len(args.pdfs)
-
-    if args.number_of_pdfs < 2:
-        exit_with_error(f"Need at least 2 PDFs to merge.")
-    elif not do_all_files_exist(args.pdfs):
-        exit_with_error()
-    elif file_exists(args.output_file) and not Confirm.ask(confirm_overwrite_txt):
-        exit_with_error()
-
-    if all(is_pdf(pdf) for pdf in args.pdfs):
-        if all(extract_page_number(pdf) for pdf in args.pdfs):
-            print_highlighted("PDFs appear to have page number suffixes so sorting numerically...")
-            args.pdfs.sort(key=lambda pdf: extract_page_number(pdf))
-        else:
-            print_highlighted("PDFs don't seem to end in page numbers so using provided order...", style='yellow')
-    else:
-        print_highlighted("WARNING: At least one of the PDF args doesn't end in '.pdf'", style='bright_yellow')
-        ask_to_proceed()
-
-    print_highlighted(f"\nMerging {args.number_of_pdfs} individual PDFs into '{args.output_file}'...")
-    return args
-
-
-###########################################
-# Parse args for extract_pdf_pages() #
-###########################################
-page_range_validator = PageRangeArgumentValidator()
-
-extract_pdf_parser = ArgumentParser(
-    formatter_class=RichHelpFormatterPlus,
-    description="Extract pages from one PDF into a new PDF.",
-)
-
-extract_pdf_parser.add_argument('pdf_file', metavar='PDF_FILE', help='PDF to extract pages from')
-
-extract_pdf_parser.add_argument('--page-range', '-r',
-                                type=page_range_validator,
-                                help=page_range_validator.HELP_MSG,
-                                required=True)
-
-extract_pdf_parser.add_argument('--destination-dir', '-d',
-                                help="directory to write the new PDF to",
-                                default=Path.cwd())
-
-extract_pdf_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
-
-
-def parse_pdf_page_extraction_args() -> Namespace:
-    args = extract_pdf_parser.parse_args()
-
-    if not is_pdf(args.pdf_file):
-        log.error(f"'{args.pdf_file}' is not a PDF.")
-        sys.exit(-1)
-    elif not Path(args.destination_dir).exists():
-        log.error(f"Destination dir '{args.destination_dir}' does not exist.")
-        sys.exit(1)
-
-    return args
-
-
-############################################
-# Parse args for extract_text_from_pdfs() #
-############################################
-extract_text_parser = ArgumentParser(
-    formatter_class=RichHelpFormatterPlus,
-    description="Extract the text from one or more files or directories.",
-    epilog="If any of the FILE_OR_DIRs is a directory all files in that directory will be extracted."
-)
-
-extract_text_parser.add_argument('file_or_dir', nargs='+', metavar='FILE_OR_DIR')
-extract_text_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
-
-extract_text_parser.add_argument('--page-range', '-r',
-                                 type=page_range_validator,
-                                 help=f"[PDFs only] {page_range_validator.HELP_MSG}")
-
-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')
-
-
-def parse_text_extraction_args() -> Namespace:
-    args = extract_text_parser.parse_args()
-    args.files_to_process = []
-
-    for file_or_dir in args.file_or_dir:
-        file_path = Path(file_or_dir)
-
-        if not file_path.exists():
-            log.error(f"File '{file_path}' doesn't exist!")
-            sys.exit(-1)
-        elif file_path.is_dir():
-            args.files_to_process.extend(files_in_dir(file_path, 'pdf'))
-        else:
-            args.files_to_process.append(file_path)
-
-    if args.page_range and (len(args.files_to_process) > 1 or not is_pdf(args.files_to_process[0])):
-        log.error(f"--page-range can only be specified for a single PDF")
-        sys.exit(-1)
-
-    return args
-
-
 #############
 #  Helpers  #
 #############

pdfalyzer-1.17.1/pdfalyzer/util/cli_tools_argument_parser.py

@@ -0,0 +1,156 @@
+"""
+Argument parsers for the command line tools other than `pdfalyze` that are included with The Pdfalyzer.
+
+1. combine_pdfs
+2.
+"""
+import sys
+from argparse import ArgumentParser, Namespace
+from pathlib import Path
+
+from rich_argparse_plus import RichHelpFormatterPlus
+from rich.prompt import Confirm
+from rich.text import Text
+from yaralyzer.helpers.file_helper import files_in_dir
+from yaralyzer.util.logging import log
+
+from pdfalyzer.util.argument_parser import ask_to_proceed, exit_with_error
+from pdfalyzer.helpers.filesystem_helper import (do_all_files_exist, extract_page_number, file_exists, is_pdf,
+     with_pdf_extension)
+from pdfalyzer.helpers.rich_text_helper import print_highlighted
+from pdfalyzer.util.page_range import PageRangeArgumentValidator
+
+MAX_QUALITY = 10
+
+
+##################
+#  combine_pdfs  #
+##################
+combine_pdfs_parser = ArgumentParser(
+    description="Combine multiple PDFs into one.",
+    epilog="If all PDFs end in a number (e.g. 'xyz_1.pdf', 'xyz_2.pdf', etc. sort the files as if those were" +
+           " page numbers prior to merging.",
+    formatter_class=RichHelpFormatterPlus)
+
+combine_pdfs_parser.add_argument('pdfs',
+                                 help='two or more PDFs to combine',
+                                 metavar='PDF_PATH',
+                                 nargs='+')
+
+combine_pdfs_parser.add_argument('-iq', '--image-quality',
+                                 help='image quality for embedded images (can compress PDF at loss of quality)',
+                                 choices=range(1, MAX_QUALITY + 1),
+                                 default=MAX_QUALITY,
+                                 type=int)
+
+combine_pdfs_parser.add_argument('-o', '--output-file',
+                                 help='path to write the combined PDFs to',
+                                 required=True)
+
+
+def parse_combine_pdfs_args() -> Namespace:
+    """Parse command line args for combine_pdfs script."""
+    args = combine_pdfs_parser.parse_args()
+    args.output_file = with_pdf_extension(args.output_file)
+    confirm_overwrite_txt = Text("Overwrite '").append(args.output_file, style='cyan').append("'?")
+    args.number_of_pdfs = len(args.pdfs)
+
+    if args.number_of_pdfs < 2:
+        exit_with_error(f"Need at least 2 PDFs to merge.")
+    elif not do_all_files_exist(args.pdfs):
+        exit_with_error()
+    elif file_exists(args.output_file) and not Confirm.ask(confirm_overwrite_txt):
+        exit_with_error()
+
+    if all(is_pdf(pdf) for pdf in args.pdfs):
+        if all(extract_page_number(pdf) for pdf in args.pdfs):
+            print_highlighted("PDFs appear to have page number suffixes so sorting numerically...")
+            args.pdfs.sort(key=lambda pdf: extract_page_number(pdf))
+        else:
+            print_highlighted("PDFs don't seem to end in page numbers so using provided order...", style='yellow')
+    else:
+        print_highlighted("WARNING: At least one of the PDF args doesn't end in '.pdf'", style='bright_yellow')
+        ask_to_proceed()
+
+    print_highlighted(f"\nMerging {args.number_of_pdfs} individual PDFs into '{args.output_file}'...")
+    return args
+
+
+#####################
+# extract_pdf_pages #
+#####################
+page_range_validator = PageRangeArgumentValidator()
+
+extract_pdf_parser = ArgumentParser(
+    formatter_class=RichHelpFormatterPlus,
+    description="Extract pages from one PDF into a new PDF.",
+)
+
+extract_pdf_parser.add_argument('pdf_file', metavar='PDF_FILE', help='PDF to extract pages from')
+
+extract_pdf_parser.add_argument('--page-range', '-r',
+                                type=page_range_validator,
+                                help=page_range_validator.HELP_MSG,
+                                required=True)
+
+extract_pdf_parser.add_argument('--destination-dir', '-d',
+                                help="directory to write the new PDF to",
+                                default=Path.cwd())
+
+extract_pdf_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
+
+
+def parse_pdf_page_extraction_args() -> Namespace:
+    args = extract_pdf_parser.parse_args()
+
+    if not is_pdf(args.pdf_file):
+        log.error(f"'{args.pdf_file}' is not a PDF.")
+        sys.exit(-1)
+    elif not Path(args.destination_dir).exists():
+        log.error(f"Destination dir '{args.destination_dir}' does not exist.")
+        sys.exit(1)
+
+    return args
+
+
+############################
+#  extract_text_from_pdfs  #
+############################
+extract_text_parser = ArgumentParser(
+    formatter_class=RichHelpFormatterPlus,
+    description="Extract the text from one or more files or directories.",
+    epilog="If any of the FILE_OR_DIRs is a directory all PDF files in that directory will be extracted."
+)
+
+extract_text_parser.add_argument('file_or_dir', nargs='+', metavar='FILE_OR_DIR')
+extract_text_parser.add_argument('--debug', action='store_true', help='turn on debug level logging')
+
+extract_text_parser.add_argument('--page-range', '-r',
+                                 type=page_range_validator,
+                                 help=f"[PDFs only] {page_range_validator.HELP_MSG}")
+
+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')
+
+
+def parse_text_extraction_args() -> Namespace:
+    args = extract_text_parser.parse_args()
+    args.files_to_process = []
+
+    for file_or_dir in args.file_or_dir:
+        file_path = Path(file_or_dir)
+
+        if not file_path.exists():
+            log.error(f"'{file_path}' is not a valid file or directory.")
+            sys.exit(-1)
+        elif file_path.is_dir():
+            args.files_to_process.extend(files_in_dir(file_path, 'pdf'))
+        else:
+            args.files_to_process.append(file_path)
+
+    if args.page_range and (len(args.files_to_process) > 1 or not is_pdf(args.files_to_process[0])):
+        log.error(f"--page-range can only be specified for a single PDF")
+        sys.exit(-1)
+
+    return args

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pdfalyzer/util/page_range.py

@@ -6,7 +6,7 @@ from argparse import ArgumentTypeError
 from dataclasses import dataclass
 from typing import Tuple
 
-PAGE_RANGE_REGEX = re.compile('\\d(-\\d)?')
+PAGE_RANGE_REGEX = re.compile(r'[1-9](\d+)?(-\d+)?')
 
 
 @dataclass
@@ -15,7 +15,7 @@ class PageRange:
 
     def __post_init__(self):
         if not PAGE_RANGE_REGEX.match(self.page_range):
-            raise ValueError(f"Invalid page range '{self.page_range}'")
+            raise ArgumentTypeError(f"Invalid page range '{self.page_range}'")
 
         if '-' in self.page_range:
             (self.first_page, self.last_page) = (int(p) for p in self.page_range.split('-'))
@@ -35,10 +35,10 @@ class PageRange:
         if self.first_page + 1 == self.last_page:
             return f"page_{self.first_page}"
         else:
-            return f"pages_{self.first_page}-{self.last_page}"
+            return f"pages_{self.first_page}-{self.last_page - 1}"
 
     def to_tuple(self) -> Tuple[int, int]:
-        return (self.first_page, self.last_page)
+        return (self.first_page - 1, self.last_page - 1)
 
     def __repr__(self) -> str:
         return f"PageRange({self.first_page}, {self.last_page})"
@@ -48,7 +48,4 @@ class PageRangeArgumentValidator(object):
     HELP_MSG = "a single digit ('11') or a range ('11-15') (WILL NOT extract the last page)"
 
     def __call__(self, value):
-        if not PAGE_RANGE_REGEX.match(value):
-            raise ArgumentTypeError("Argument has to match '{}'".format(PAGE_RANGE_REGEX.pattern))
-
         return PageRange(value)

{pdfalyzer-1.17.0 → pdfalyzer-1.17.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdfalyzer"
-version = "1.17.0"
+version = "1.17.1"
 description = "PDF analysis tool. Scan a PDF with YARA rules, visualize its inner tree-like data structure in living color (lots of colors), force decodes of suspicious font binaries, and more."
 authors = ["Michel de Cryptadamus <michel@cryptadamus.com>"]
 license = "GPL-3.0-or-later"
@@ -74,6 +74,10 @@ yaralyzer = "^1.0.9"
 
 [tool.poetry.extras]
 extract = ["PyMuPDF", "pytesseract"]
+# Poetry 2.x handles optional dependencies like this:
+# [project.optional-dependencies]
+# extract = ["PyMuPDF", "pytesseract"]
+
 
 [tool.poetry.group.dev.dependencies]
 flake8 = "^7.3.0"
@@ -114,8 +118,3 @@ requires = ["poetry-core>=1.0.0"]
 addopts = [
     "--import-mode=importlib",
 ]
-
-
-# Poetry 2.x handles optional dependencies like this:
-# [project.optional-dependencies]
-# extract = ["PyMuPDF", "pytesseract"]