diff --git a/Makefile b/Makefile index fc3fae8..641c690 100644 --- a/Makefile +++ b/Makefile @@ -10,9 +10,14 @@ clean: rm -rf *.egg-info lint: + isort pdfmajor black pdfmajor bandit -r pdfmajor mypy pdfmajor + isort tests + black tests + bandit -r tests + mypy tests test: ./venv/bin/python -m unittest discover tests diff --git a/pdfmajor/lexer/__init__.py b/pdfmajor/lexer/__init__.py index 1a1c6b8..3e899bd 100644 --- a/pdfmajor/lexer/__init__.py +++ b/pdfmajor/lexer/__init__.py @@ -1,18 +1,19 @@ from typing import Iterator -from pdfmajor.lexer.dict_and_hex import parse_double_angled_bracket -from pdfmajor.lexer.string import parse_string -from pdfmajor.lexer.keyword import parse_keyword -from pdfmajor.lexer.number import parse_number -from pdfmajor.lexer.name import parse_name + from pdfmajor.lexer.comment import parse_comment +from pdfmajor.lexer.dict_and_hex import parse_double_angled_bracket +from pdfmajor.lexer.keyword import parse_keyword +from pdfmajor.lexer.name import parse_name +from pdfmajor.lexer.number import parse_number from pdfmajor.lexer.regex import NONSPC +from pdfmajor.lexer.string import parse_string from pdfmajor.lexer.token import ( TArrayValue, TDictValue, Token, - TokenDictionary, - TokenKeyword, TokenArray, + TokenDictionary, + TokenKeyword ) from pdfmajor.streambuffer import BufferStream diff --git a/pdfmajor/lexer/comment.py b/pdfmajor/lexer/comment.py index 3dbe9d8..11ca3d9 100644 --- a/pdfmajor/lexer/comment.py +++ b/pdfmajor/lexer/comment.py @@ -1,8 +1,6 @@ from pdfmajor.lexer.exceptions import LexerEOF from pdfmajor.lexer.regex import EOL -from pdfmajor.lexer.token import ( - TokenComment, -) +from pdfmajor.lexer.token import TokenComment from pdfmajor.streambuffer import BufferStream diff --git a/pdfmajor/lexer/dict_and_hex.py b/pdfmajor/lexer/dict_and_hex.py index 013269e..8f5194f 100644 --- a/pdfmajor/lexer/dict_and_hex.py +++ b/pdfmajor/lexer/dict_and_hex.py @@ -1,8 +1,9 @@ -from pdfmajor.streambuffer import BufferStream +from typing import Union + from pdfmajor.lexer.exceptions import LexerEOF from pdfmajor.lexer.regex import END_HEX_STRING, HEX_PAIR, SPC from pdfmajor.lexer.token import TDictValue, TokenDictionary, TokenHexString -from typing import Union +from pdfmajor.streambuffer import BufferStream def parse_double_angled_bracket( diff --git a/pdfmajor/lexer/keyword.py b/pdfmajor/lexer/keyword.py index 25f0f58..c3f80f4 100644 --- a/pdfmajor/lexer/keyword.py +++ b/pdfmajor/lexer/keyword.py @@ -1,14 +1,10 @@ -from pdfmajor.streambuffer import BufferStream -from pdfmajor.lexer.exceptions import LexerEOF -from pdfmajor.lexer.token import ( - Token, - TokenBoolean, - TokenKeyword, - TokenNull, -) -from pdfmajor.lexer.regex import END_KEYWORD from typing import Optional, Union +from pdfmajor.lexer.exceptions import LexerEOF +from pdfmajor.lexer.regex import END_KEYWORD +from pdfmajor.lexer.token import Token, TokenBoolean, TokenKeyword, TokenNull +from pdfmajor.streambuffer import BufferStream + def parse_keyword(buffer: BufferStream, initialpos: Optional[int] = None) -> Token: """Parses input stream into a keyword or bool diff --git a/pdfmajor/lexer/name.py b/pdfmajor/lexer/name.py index 6724258..9238758 100644 --- a/pdfmajor/lexer/name.py +++ b/pdfmajor/lexer/name.py @@ -1,17 +1,11 @@ from dataclasses import dataclass -from pdfmajor.lexer.exceptions import ( - InvalidHexToken, - LexerEOF, - LexerError, -) - -from pdfmajor.streambuffer import BufferStream -from pdfmajor.lexer.token import TokenName -from pdfmajor.lexer.regex import HEX, END_LITERAL - - from typing import Optional +from pdfmajor.lexer.exceptions import InvalidHexToken, LexerEOF, LexerError +from pdfmajor.lexer.regex import END_LITERAL, HEX +from pdfmajor.lexer.token import TokenName +from pdfmajor.streambuffer import BufferStream + @dataclass class LiteralParseState: diff --git a/pdfmajor/lexer/number.py b/pdfmajor/lexer/number.py index e075e44..3f23aa4 100644 --- a/pdfmajor/lexer/number.py +++ b/pdfmajor/lexer/number.py @@ -1,15 +1,10 @@ from decimal import Decimal from typing import Optional -from pdfmajor.streambuffer import BufferStream + from pdfmajor.lexer.exceptions import InvalidToken, LexerEOF, LexerError -from pdfmajor.lexer.token import ( - TokenReal, - TokenNumber, - TokenInteger, -) -from pdfmajor.lexer.regex import ( - END_NUMBER, -) +from pdfmajor.lexer.regex import END_NUMBER +from pdfmajor.lexer.token import TokenInteger, TokenNumber, TokenReal +from pdfmajor.streambuffer import BufferStream def parse_number( diff --git a/pdfmajor/lexer/string.py b/pdfmajor/lexer/string.py index 77153ab..6cbcaea 100644 --- a/pdfmajor/lexer/string.py +++ b/pdfmajor/lexer/string.py @@ -1,8 +1,9 @@ from dataclasses import dataclass from typing import Optional + +from pdfmajor.lexer.exceptions import LexerEOF, LexerError from pdfmajor.lexer.regex import END_STRING, ESC_STRING, OCT_STRING from pdfmajor.lexer.token import TokenString -from pdfmajor.lexer.exceptions import LexerEOF, LexerError from pdfmajor.streambuffer import BufferStream diff --git a/pdfmajor/lexer/token.py b/pdfmajor/lexer/token.py index 629da93..ad65851 100644 --- a/pdfmajor/lexer/token.py +++ b/pdfmajor/lexer/token.py @@ -1,6 +1,6 @@ +from decimal import Decimal from enum import Enum from typing import Any, Generic, NamedTuple, TypeVar, Union -from decimal import Decimal T = TypeVar("T") diff --git a/pdfmajor/parser/exceptions.py b/pdfmajor/parser/exceptions.py index 1ce38a4..d1eb6c8 100644 --- a/pdfmajor/parser/exceptions.py +++ b/pdfmajor/parser/exceptions.py @@ -1,6 +1,7 @@ from typing import List + +from pdfmajor.exceptions import BrokenFile, PDFMajorException from pdfmajor.lexer.token import TokenKeyword -from pdfmajor.exceptions import PDFMajorException, BrokenFile class ParserError(PDFMajorException): diff --git a/pdfmajor/parser/fliters/__init__.py b/pdfmajor/parser/fliters/__init__.py index 7fe48b6..0b41c36 100644 --- a/pdfmajor/parser/fliters/__init__.py +++ b/pdfmajor/parser/fliters/__init__.py @@ -1,16 +1,13 @@ import zlib - -from typing import Any, Dict, List, Optional from base64 import a85decode from binascii import a2b_hex -from ..exceptions import InvalidDecoderOrNotImplemented +from typing import Any, Dict, List, Optional -from .types import FilterType +from ..exceptions import InvalidDecoderOrNotImplemented +from .ccit import ccittfaxdecode from .lzw import lzwdecode from .rld import rldecode -from .ccit import ccittfaxdecode -from ..exceptions import InvalidDecoderOrNotImplemented - +from .types import FilterType _filter_type_name_mapping: Dict[str, FilterType] = { "FlateDecode": FilterType.FlateDecode, diff --git a/pdfmajor/parser/fliters/ccit.py b/pdfmajor/parser/fliters/ccit.py index cf94ef2..dd38557 100644 --- a/pdfmajor/parser/fliters/ccit.py +++ b/pdfmajor/parser/fliters/ccit.py @@ -10,7 +10,6 @@ import array - from typing import Optional from ..exceptions import DecodeFailed diff --git a/pdfmajor/parser/fliters/lzw.py b/pdfmajor/parser/fliters/lzw.py index 000eaf1..4955b1d 100644 --- a/pdfmajor/parser/fliters/lzw.py +++ b/pdfmajor/parser/fliters/lzw.py @@ -1,7 +1,9 @@ from io import BytesIO from typing import List, Optional + from ..exceptions import DecodeFailed + ## LZWDecoder ## class LZWDecoder(object): diff --git a/pdfmajor/parser/objects/collections.py b/pdfmajor/parser/objects/collections.py index ebb37d8..be250e2 100644 --- a/pdfmajor/parser/objects/collections.py +++ b/pdfmajor/parser/objects/collections.py @@ -1,4 +1,5 @@ from typing import Any, Dict, List, Optional + from ..exceptions import ParserError from .base import PDFContextualObject, PDFObject from .primitives import PDFName @@ -13,6 +14,13 @@ class PDFArray(List[PDFObject], PDFContextualObject): def to_python(self) -> List[Any]: return [x.to_python() for x in self] + @classmethod + def from_list(cls, data: List[PDFObject]): + out = cls() + for item in data: + out.pass_item(item) + return out + class PDFDictionary(Dict[str, PDFObject], PDFContextualObject): """A class representing a PDF Dictionary as specified in PDF spec 1.7 section 7.3.7""" diff --git a/pdfmajor/parser/objects/comment.py b/pdfmajor/parser/objects/comment.py index c7b6c9e..a1b9dc1 100644 --- a/pdfmajor/parser/objects/comment.py +++ b/pdfmajor/parser/objects/comment.py @@ -1,4 +1,5 @@ from typing import Optional, Tuple + from .base import PDFObject diff --git a/pdfmajor/parser/objects/indirect.py b/pdfmajor/parser/objects/indirect.py index 8db7afb..9a2d3a2 100644 --- a/pdfmajor/parser/objects/indirect.py +++ b/pdfmajor/parser/objects/indirect.py @@ -1,6 +1,7 @@ from typing import Optional from pdfmajor.parser.stream.PDFStream import PDFStream + from .base import PDFContextualObject, PDFObject diff --git a/pdfmajor/parser/objects/primitives.py b/pdfmajor/parser/objects/primitives.py index 5b0f0b5..60381ab 100644 --- a/pdfmajor/parser/objects/primitives.py +++ b/pdfmajor/parser/objects/primitives.py @@ -3,17 +3,17 @@ from typing import Dict, Generic, Optional, Type, TypeVar from pdfmajor.lexer.token import ( Token, - TokenPrimitive, TokenBoolean, TokenHexString, TokenInteger, TokenName, TokenNull, + TokenPrimitive, TokenReal, TokenString, ) -from .base import PDFObject +from .base import PDFObject T = TypeVar("T", str, bytes, int, bool, Decimal) @@ -80,7 +80,7 @@ _token_to_obj_map: Dict[Type[Token], Type[PDFPrimitiveObject]] = { } -def get_obj_from_token_primitive(token: Token) -> Optional[PDFObject]: +def get_obj_from_token_primitive(token: Token) -> Optional[PDFPrimitiveObject]: """converts tokens to their primitive object counterparts Args: @@ -91,7 +91,7 @@ def get_obj_from_token_primitive(token: Token) -> Optional[PDFObject]: """ obj_const = _token_to_obj_map.get(type(token), None) if obj_const: - return obj_const.from_token(token) # type: ignore + return obj_const.from_token(token) elif isinstance(token, TokenNull): return PDFNull() else: diff --git a/pdfmajor/parser/stream/PDFStream.py b/pdfmajor/parser/stream/PDFStream.py index 391183d..38f903c 100644 --- a/pdfmajor/parser/stream/PDFStream.py +++ b/pdfmajor/parser/stream/PDFStream.py @@ -1,6 +1,7 @@ -from pdfmajor.parser.objects.base import PDFObject from typing import Any, List, Optional, TypeVar, Union +from pdfmajor.parser.objects.base import PDFObject + from ..objects.collections import PDFDictionary from ..objects.primitives import PDFNull diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..f57d088 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,2 @@ +[tool.isort] +multi_line_output = 3 diff --git a/tests/old/test_bad_unicode.py b/tests/old/test_bad_unicode.py deleted file mode 100644 index fcaf674..0000000 --- a/tests/old/test_bad_unicode.py +++ /dev/null @@ -1,24 +0,0 @@ -from pathlib import Path -from unittest import TestCase, main - -from pdfmajor.interpreter import PDFInterpreter -from pdfmajor.execptions import UnicodeNotDefined - -CURRENT_FOLDER = Path("./") - -class BadUnicode(TestCase): - def test_ensure_failure(self): - pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=False) - pages = list(pdf) - with self.assertRaises(UnicodeNotDefined): - list(pages[2]) - - def test_ensure_no_failure(self): - pdf = PDFInterpreter(CURRENT_FOLDER / "tests" / "samples" / "pdf" / "bad-unicode.pdf", ignore_bad_chars=True) - pages = list(pdf) - list(pages[2]) - - -if __name__ == '__main__': - # Run Tests - main() diff --git a/tests/old/test_caching_err.py b/tests/old/test_caching_err.py deleted file mode 100644 index 8de878f..0000000 --- a/tests/old/test_caching_err.py +++ /dev/null @@ -1,38 +0,0 @@ -import os -from unittest import TestCase, main -# from pdfmajor.extractor import extract_items_from_pdf -from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging -from pdfmajor.interpreter import PageInterpreter -from pdfmajor.interpreter.commands import LTContainer - -CUR_PATH = os.path.dirname(os.path.dirname(__file__)) -INPUT_FOLDER = os.path.join( - CUR_PATH, "tests/samples/pdf" -) -FILES = os.listdir(INPUT_FOLDER) -NUM_LOOPS = 10 - -def count_elms(file_path: str): - count = 0 - for page in PDFInterpreter(file_path, ignore_bad_chars=True): - for item in page: - if isinstance(item, LTContainer): - count += len([*item]) - else: - count += 1 - return count - -class CachingTester(TestCase): - def test_cache(self): - for file_name in FILES: - self.subTest(name = file_name) - file_path = os.path.join(INPUT_FOLDER, file_name) - last_count = count_elms(file_path) - for _ in range(NUM_LOOPS): - new_count = count_elms(file_path) - self.assertEqual( new_count , last_count ) - last_count = new_count - -if __name__ == '__main__': - # Run Tests - main() diff --git a/tests/old/test_cols.py b/tests/old/test_cols.py deleted file mode 100644 index bab0dd2..0000000 --- a/tests/old/test_cols.py +++ /dev/null @@ -1,115 +0,0 @@ -import os -from typing import List -from unittest import TestCase, main - -# from pdfmajor.extractor import extract_items_from_pdf -from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging -from pdfmajor.interpreter import PageInterpreter -from pdfmajor.interpreter.commands import LTCurve, PDFColor, LTXObject -from pdfmajor.interpreter.commands import PREDEFINED_COLORSPACE - -CUR_PATH = os.path.dirname(os.path.dirname(__file__)) -INPUT_FOLDER = os.path.join( - CUR_PATH, "tests/samples/pdf" -) -FILES = os.listdir(INPUT_FOLDER) -NUM_LOOPS = 10 - -class ColorTest(TestCase): - def run_test(self, file_path: str, curve_defs: List[List[PDFColor]]): - def run_once(item): - if isinstance(item, LTCurve): - t_stroke, t_fill = curve_defs.pop(0) - self.assertEqual( item.stroke.values, t_stroke.values ) - self.assertEqual( item.stroke.color_space, t_stroke.color_space ) - self.assertEqual( item.fill.values, t_fill.values ) - self.assertEqual( item.fill.color_space, t_fill.color_space ) - elif isinstance(item, LTXObject): - for c in item: - run_once(c) - - for page in PDFInterpreter(file_path): - for item in page: - run_once(item) - - def test_lorem_v3(self): - self.run_test( - os.path.join(INPUT_FOLDER, "lorem-v3.pdf"), - [ - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ], - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207), - ], - [ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207), - ], - [ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 0), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 114, 159, 207), - ], - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ], - [ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 0, 0), - ] - ] + - ([[ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ]]*24)+ - ([[ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 128), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0), - ]]*11)+ - ([[ - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 0, 0, 0), - ]]*5)+ - [[ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ]] - ) - - def test_lorem_v4(self): - self.run_test( - os.path.join(INPUT_FOLDER, "lorem-v4.pdf"), - [ - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ], - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 64, 64, 64), - ] - ] - ) - - def test_lorem_v5(self): - self.run_test( - os.path.join(INPUT_FOLDER, "lorem-v5.pdf"), - [ - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 255, 255, 255), - ], - [ - PDFColor(None), - PDFColor(PREDEFINED_COLORSPACE['DeviceRGB'], 128, 128, 128), - ] - ] - ) - - -if __name__ == '__main__': - # Run Tests - main() diff --git a/tests/old/test_conversions.py b/tests/old/test_conversions.py deleted file mode 100755 index 1db6e5f..0000000 --- a/tests/old/test_conversions.py +++ /dev/null @@ -1,61 +0,0 @@ -#!/usr/bin/env python -import re -import os -import logging - -from unittest import TestCase, main -from typing import List -from pdfmajor.converters import convert_file -from xml.etree import ElementTree -from json import load as json_load -from tqdm import tqdm - -def rel_path(*arg: str) -> str: - return os.path.normpath(os.path.join(os.path.dirname(__file__), *arg)) - -EXTS = ['text', 'json','xml','html'] -INPUT_FOLDER = rel_path("./samples/pdf") -OUTPUT_FOLDER = rel_path(f"./samples/output/") - -if not os.path.exists(OUTPUT_FOLDER): - os.makedirs(OUTPUT_FOLDER) - -files = os.listdir(INPUT_FOLDER) - -TOTAL = len(files)*len(EXTS) - -class ConversionTest(TestCase): - def test_conversion(self): - # with tqdm(total=TOTAL) as waiter: - for idx, file_name in enumerate(files): - self.subTest(i=idx); - file_name_no_ext = re.sub(r'\.pdf$',"", file_name) - input_file_path = os.path.join(INPUT_FOLDER, file_name) - - for ext in EXTS: - if not os.path.exists(os.path.join(OUTPUT_FOLDER, ext)): - os.makedirs(os.path.join(OUTPUT_FOLDER, ext)) - output_file_path = os.path.join(OUTPUT_FOLDER, ext, file_name_no_ext + "." + ext) - if len(file_name) > len(file_name_no_ext): - # waiter.set_description(f"Conversion test -- {file_name}") - convert_file( - input_file=input_file_path, - output_file=output_file_path, - out_type=ext, - ignore_bad_chars=True, - debug_level=logging.WARN, - ) - if ext == 'xml': - # waiter.set_description(f" > testing format {file_name}") - ElementTree.parse(output_file_path) - elif ext == 'json': - # waiter.set_description(f" > testing format {file_name}") - with open(output_file_path, 'r') as outf: - json_load(outf) - # waiter.update() - # waiter.set_description("Done") - - -if __name__ == '__main__': - # Run Tests - main() \ No newline at end of file diff --git a/tests/old/test_html_writer.py b/tests/old/test_html_writer.py deleted file mode 100644 index 6e9e91b..0000000 --- a/tests/old/test_html_writer.py +++ /dev/null @@ -1,82 +0,0 @@ -from contextlib import contextmanager -from unittest import TestCase, main -from typing import List, Tuple, Callable -from os import remove -from tempfile import mktemp -from pdfmajor.converters.writers.html import HTMLMaker -from tqdm import tqdm - -# Make temp file -FILE_NAME = mktemp() - -TestFunction = Callable[[HTMLMaker], str]; -TESTS: List[Tuple[TestFunction, str]] = []; - -class HTMLTester(TestCase): - @contextmanager - def get_html(self): - with HTMLMaker(FILE_NAME) as html: - yield html - def compare(self, expected: str): - with open(FILE_NAME, 'r') as f: - self.assertEqual(f.read() , expected) - - def test_html_basic(self): - with self.get_html() as html: - with html.elm("html", nolineend=True): - html.write("test") - self.compare(""" - test -""") - - def test_html_with_attributes(self): - with self.get_html() as html: - with html.elm("html", nolineend=True): - with html.elm("head"): - html.singleton("meta", { - 'http-equiv': "Content-Type", - 'content': "text/html" - }) - self.compare(""" - - - -""") - - def test_html_with_children(self): - with self.get_html() as html: - with html.elm("html", nolineend=True): - with html.elm("head"): - html.singleton("meta", { - 'http-equiv': "Content-Type", - 'content': "text/html" - }) - with html.elm("body"): - with html.elm("h1", css={"color": "red"}): - html.write("Hello World") - self.compare(""" - - - - -

- Hello World -

- -""") - - def test_html_with_css(self): - with self.get_html() as html: - with html.elm('style'): - html.write('''.page { position: relative; overflow: hidden;border: 1px black solid;}''') - self.compare(""" -""") - - -if __name__ == '__main__': - # Run Tests - main() - # Clean up - remove(FILE_NAME) \ No newline at end of file diff --git a/tests/old/test_image_writer.py b/tests/old/test_image_writer.py deleted file mode 100644 index 2924c77..0000000 --- a/tests/old/test_image_writer.py +++ /dev/null @@ -1,41 +0,0 @@ -import os -from unittest import TestCase, main - -from pdfmajor.interpreter import LTImage, logging -from pdfmajor.interpreter import PageInterpreter, PDFInterpreter -from pdfmajor.interpreter.commands import LTItem -from pdfmajor.interpreter.commands import LTCharBlock, LTChar - -CUR_PATH = os.path.dirname(os.path.dirname(__file__)) -FILES = [ - "jpg", - "looseless" -] -OUTPUT_FOLDER = os.path.join( - CUR_PATH, - 'samples/output/images' -) - -if not os.path.exists(OUTPUT_FOLDER): - os.makedirs(OUTPUT_FOLDER) - -class ImageTester(TestCase): - def test_image_extract(self): - for file_name in FILES: - self.subTest(file_name=file_name) - for page in PDFInterpreter(os.path.join( - CUR_PATH, - f"tests/samples/pdf/{file_name}.pdf" - ), debug_level=logging.ERROR): - self.assertTrue( isinstance(page, PageInterpreter) ) - for item_idx, item in enumerate(page): - self.assertTrue( isinstance(item, LTItem) ) - if isinstance(item, LTImage): - item.save_image( - OUTPUT_FOLDER, - file_name=f'{file_name}_p{page.page_num}i{item_idx}' - ) - -if __name__ == '__main__': - # Run Tests - main() diff --git a/tests/old/test_interpreter.py b/tests/old/test_interpreter.py deleted file mode 100644 index cf46e4b..0000000 --- a/tests/old/test_interpreter.py +++ /dev/null @@ -1,29 +0,0 @@ -import os -from unittest import TestCase, main -from pdfmajor.interpreter import LTCharBlock, PDFInterpreter, logging -from pdfmajor.interpreter import PageInterpreter -from pdfmajor.interpreter.commands import LTItem -from pdfmajor.interpreter.commands import LTCharBlock, LTChar - -CUR_PATH = os.path.dirname(os.path.dirname(__file__)) -INPUT_FOLDER = os.path.join( - CUR_PATH, "tests/samples/pdf" -) -FILES = os.listdir(INPUT_FOLDER) - -class TestInterpreter(TestCase): - def test_pdfintp(self): - for file_name in FILES: - self.subTest(file_name=file_name) - file_path = os.path.join(INPUT_FOLDER, file_name) - for page in PDFInterpreter(file_path, debug_level=logging.ERROR, ignore_bad_chars=True): - self.assertTrue( isinstance(page, PageInterpreter) ) - for item in page: - self.assertTrue( isinstance(item, LTItem) ) - if isinstance(item, LTCharBlock): - for char in item: - self.assertTrue( isinstance(char, LTChar) ) - -if __name__ == '__main__': - # Run Tests - main() diff --git a/tests/old/test_json_writer.py b/tests/old/test_json_writer.py deleted file mode 100644 index 93ac009..0000000 --- a/tests/old/test_json_writer.py +++ /dev/null @@ -1,111 +0,0 @@ -from os import remove -from tempfile import mktemp -from pdfmajor.converters.writers.json import JSONMaker - -# Make temp file -FILE_NAME = mktemp() - -with JSONMaker(FILE_NAME) as obj: - obj.number("a", 2) - obj.string("hello", "world") -assert(open(FILE_NAME, 'r').read() == """{ - "a": 2, - "hello": "world" -}""") - -with JSONMaker(FILE_NAME) as obj: - with obj.object("test") as child: - child.number("A", 2) -assert(open(FILE_NAME, 'r').read() == """{ - "test": { - "A": 2 - } -}""") - -with JSONMaker(FILE_NAME) as obj: - with obj.object("hello") as child: - with child.object("nested") as nested: - with nested.object("so") as so: - so.string("really", 'nested'), - so.number("man", 2) - nested.number("he", 3) - child.string('fo', 'real') - obj.string('fo', 'real2') -assert(open(FILE_NAME, 'r').read() == """{ - "hello": { - "nested": { - "so": { - "really": "nested", - "man": 2 - }, - "he": 3 - }, - "fo": "real" - }, - "fo": "real2" -}""") - -with JSONMaker(FILE_NAME) as obj: - with obj.array("hello") as child: - child.number(1) - with child.array() as nchild: - nchild.string('wow') - child.number(3) -assert(open(FILE_NAME, 'r').read() == """{ - "hello": [ - 1, - [ - "wow" - ], - 3 - ] -}""") - -with JSONMaker(FILE_NAME) as obj: - with obj.array("pages") as pages: - with pages.object() as page: - page.number("id", 1) - page.number("height", 20) - page.number("width", 20) - with page.array("children") as children: - with children.object() as item: - item.string("type", "char-block") - item.string("text", "test") - item.string("color_type", "rgb") - with item.array("color_vals") as col_vals: - col_vals.number(0) - col_vals.number(0) - col_vals.number(0) - item.number("x0", 2) - item.number("x1", 4.2) - item.number("y0", 231.12) - item.number("y1", 331.12) -assert(open(FILE_NAME, 'r').read() == """{ - "pages": [ - { - "id": 1, - "height": 20, - "width": 20, - "children": [ - { - "type": "char-block", - "text": "test", - "color_type": "rgb", - "color_vals": [ - 0, - 0, - 0 - ], - "x0": 2, - "x1": 4.2, - "y0": 231.12, - "y1": 331.12 - } - ] - } - ] -}""") - - -# Clean up -remove(FILE_NAME) \ No newline at end of file diff --git a/tests/old/test_yml_writer.py b/tests/old/test_yml_writer.py deleted file mode 100644 index 591ff53..0000000 --- a/tests/old/test_yml_writer.py +++ /dev/null @@ -1,101 +0,0 @@ -from os import remove -from tempfile import mktemp -from pdfmajor.converters.writers.yaml import YAMLMaker - -# Make temp file -FILE_NAME = mktemp() - - -with YAMLMaker(FILE_NAME) as yml: - yml.write("name", "bob") - yml.write("age", "20") - with yml.object("wife") as wife: - wife.write("name", "kory") - wife.write("age", "21") - with yml.array("children") as children: - with children.object() as child: - child.write("name", "Mike") - with child.array("toys") as toys: - toys.write("lion") - toys.write("bear") - with yml.object("computer") as computer: - computer.write("type", "awesome") -assert(open(FILE_NAME, 'r').read() == """name: bob -age: 20 -wife: - name: kory - age: 21 -children: - - name: Mike - toys: - - lion - - bear -computer: - type: awesome""") - -with YAMLMaker(FILE_NAME) as yml: - yml.write("name", "bob") - yml.write("age", "20") - yml.place_object("wife", { - "name": "kory", - "age": 21 - }) - with yml.array("children") as children: - with children.object() as child: - child.write("name", "Mike") - child.place_array("toys", [ - "lion", "bear" - ]) - yml.place_object("computer", {"type": "awesome"}) -assert(open(FILE_NAME, 'r').read() == """name: bob -age: 20 -wife: - name: kory - age: 21 -children: - - name: Mike - toys: - - lion - - bear -computer: - type: awesome""") - -with YAMLMaker(FILE_NAME) as yml: - with yml.array('pages') as pages: - with pages.object() as page: - page.write("id", 0) - page.write("width", 100) - page.write("height", 200) - with page.array("children") as children: - with children.object() as curve: - with curve.object("stroke") as fill: - fill.write("type", "DeviceRGB") - fill.write("value", ['1','2','3']) - curve.write("x0", 0) - curve.write("x1", 1) - with curve.object("fill") as fill: - fill.write("type", "DeviceRGB") - fill.write("value", ['1','2','3']) - curve.write("y0", 0) - curve.write("y1", 1) - -assert(open(FILE_NAME, 'r').read() == """pages: - - id: 0 - width: 100 - height: 200 - children: - - stroke: - type: DeviceRGB - value: ['1', '2', '3'] - x0: 0 - x1: 1 - fill: - type: DeviceRGB - value: ['1', '2', '3'] - y0: 0 - y1: 1""") - - - -# Clean up -remove(FILE_NAME) \ No newline at end of file