ComPDFKitConversion 4.3.0__cp313-cp313-macosx_11_0_arm64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- ComPDFKitConversion/.dylibs/libc++.1.0.dylib +0 -0
- ComPDFKitConversion/__init__.py +25 -0
- ComPDFKitConversion/__init__.pyi +23 -0
- ComPDFKitConversion/_core.cpython-313-darwin.so +0 -0
- ComPDFKitConversion/_core.pyi +1125 -0
- ComPDFKitConversion/libDocumentAI.4.3.0.dylib +0 -0
- ComPDFKitConversion/libcpdfconversionsdk.dylib +4 -0
- ComPDFKitConversion/libonnxruntime.1.18.0.dylib +0 -0
- ComPDFKitConversion/libopencv_world.410.dylib +0 -0
- ComPDFKitConversion/py.typed +0 -0
- compdfkitconversion-4.3.0.dist-info/METADATA +70 -0
- compdfkitconversion-4.3.0.dist-info/RECORD +14 -0
- compdfkitconversion-4.3.0.dist-info/WHEEL +6 -0
- compdfkitconversion-4.3.0.dist-info/top_level.txt +1 -0
|
Binary file
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
"""
|
|
2
|
+
Conversion Python SDK
|
|
3
|
+
|
|
4
|
+
This package provides Python bindings for the Conversion SDK, enabling
|
|
5
|
+
conversion of PDF files to formats including Word, Excel, PPT, HTML,
|
|
6
|
+
images, and more.
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
import os
|
|
10
|
+
import platform
|
|
11
|
+
|
|
12
|
+
# On Windows, add this package's directory to the DLL search path
|
|
13
|
+
# so that cpdfconversionsdk.dll and other dependent DLLs can be found.
|
|
14
|
+
_package_dir = os.path.dirname(os.path.abspath(__file__))
|
|
15
|
+
|
|
16
|
+
if platform.system() == "Windows":
|
|
17
|
+
# Python 3.8+ requires explicit DLL directory registration
|
|
18
|
+
if hasattr(os, "add_dll_directory"):
|
|
19
|
+
os.add_dll_directory(_package_dir)
|
|
20
|
+
# Also prepend to PATH as a fallback for older Python or subprocess calls
|
|
21
|
+
os.environ["PATH"] = _package_dir + os.pathsep + os.environ.get("PATH", "")
|
|
22
|
+
|
|
23
|
+
# Import everything from the native extension module.
|
|
24
|
+
from ._core import * # noqa: F401, F403
|
|
25
|
+
from ._core import __doc__ as _module_doc # noqa: F401
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
"""
|
|
2
|
+
|
|
3
|
+
Conversion SDK Python bindings
|
|
4
|
+
|
|
5
|
+
"""
|
|
6
|
+
from ._core import *
|
|
7
|
+
from ._core import (
|
|
8
|
+
CPDFConversion as CPDFConversion,
|
|
9
|
+
ConvertCallback as ConvertCallback,
|
|
10
|
+
ConvertOptions as ConvertOptions,
|
|
11
|
+
ErrorCode as ErrorCode,
|
|
12
|
+
ExcelWorksheetOption as ExcelWorksheetOption,
|
|
13
|
+
HtmlOption as HtmlOption,
|
|
14
|
+
ImageColorMode as ImageColorMode,
|
|
15
|
+
ImageType as ImageType,
|
|
16
|
+
LibraryManager as LibraryManager,
|
|
17
|
+
OCRLanguage as OCRLanguage,
|
|
18
|
+
OCROption as OCROption,
|
|
19
|
+
PageLayoutMode as PageLayoutMode,
|
|
20
|
+
WordPdfBookmarkMode as WordPdfBookmarkMode,
|
|
21
|
+
LicenseType as LicenseType,
|
|
22
|
+
Line as Line,
|
|
23
|
+
)
|
|
Binary file
|
|
@@ -0,0 +1,1125 @@
|
|
|
1
|
+
"""
|
|
2
|
+
|
|
3
|
+
Conversion SDK Python bindings
|
|
4
|
+
|
|
5
|
+
"""
|
|
6
|
+
from __future__ import annotations
|
|
7
|
+
import collections.abc
|
|
8
|
+
import typing
|
|
9
|
+
__all__: list[str] = ['ALL', 'ARABIC', 'AUTO', 'BALANCED', 'BINARY', 'BMP', 'BOX', 'CANCEL', 'CHINESE', 'CHINESE_TRA', 'COLOR', 'COMPRESS_ERROR', 'CONVERTING_ERROR', 'CPDFConversion', 'CYRILLIC', 'ConvertCallback', 'ConvertOptions', 'DEVANAGARI', 'ENGLISH', 'ESLAV', 'EXPIRE_ERROR', 'ErrorCode', 'ExcelWorksheetOption', 'FILE_ERROR', 'FLOW', 'FOR_DOCUMENT', 'FOR_PAGE', 'FOR_TABLE', 'GIF', 'GRAY', 'GREEK', 'HEADINGS', 'HIGH_ACCURACY', 'HtmlOption', 'IMAGE_DATA_EMPTY', 'IMAGE_FORMAT_UNSUPPORTED', 'IMAGE_INVALID', 'IMAGE_WIDTH_HEIGHT_ERROR', 'INVALID_ARG', 'INVALID_CHARACTER', 'INVALID_CHARACTER_AND_SCAN_PAGE', 'INVALID_HANDLE', 'INVALID_MODEL_FORMAT', 'INVALID_TABLE', 'IO_ERROR', 'ImageColorMode', 'ImageType', 'JAPANESE', 'JPEG', 'JPEG2000', 'JPG', 'KANNADA', 'KOREAN', 'LATIN', 'LICENSE_CONCURRENCY_EXCEEDED', 'LICENSE_EXPIRE', 'LICENSE_FILE_READ_FAILED', 'LICENSE_ILLEGAL_ACCESS', 'LICENSE_INVALID', 'LICENSE_MISMATCH', 'LICENSE_OCR_PERMISSION_DENY', 'LICENSE_PAGE_LIMIT_EXCEEDED', 'LICENSE_PERMISSION_DENY', 'LICENSE_QUOTA_CORRUPTED', 'LICENSE_UNINITIALIZED', 'LICENSE_UNSUPPORTED_API', 'LICENSE_UNSUPPORTED_DEVICE', 'LICENSE_UNSUPPORTED_ID', 'LICENSE_UNSUPPORTED_PLATFORM', 'LibraryManager', 'LicenseType', 'MISSING_ARG', 'MODEL_FORMAT_UNSUPPORTED', 'MODEL_FUNCTION_UNSUPPORTED', 'MODEL_SDK_MISMATCH', 'MULTIPLE_PAGE', 'MULTIPLE_PAGE_WITH_BOOKMARK', 'NONE', 'NO_TABLE_ERROR', 'OCRLanguage', 'OCROption', 'OCR_FAILURE', 'OUT_OF_MEMORY', 'PDF_FORMAT_ERROR', 'PDF_PAGE_ERROR', 'PDF_PASSWORD_ERROR', 'PDF_SECURITY_ERROR', 'PNG', 'PageLayoutMode', 'SCAN_PAGE', 'SINGLE_PAGE', 'SINGLE_PAGE_WITH_BOOKMARK', 'SUCCESS', 'TAMIL', 'TELUGU', 'TGA', 'THAI', 'TIFF', 'TableRecognitionAccuracy', 'UNKNOWN', 'UNKNOWN_ERROR', 'UNSUPPORTED_FEATURE', 'WEBP', 'WORD_BOOKMARKS', 'WordPdfBookmarkMode']
|
|
10
|
+
class CPDFConversion:
|
|
11
|
+
"""
|
|
12
|
+
|
|
13
|
+
CPDFConversion class provides functionalities to convert PDF files into various formats such as Word, Excel, PPT, HTML, etc.
|
|
14
|
+
"""
|
|
15
|
+
@staticmethod
|
|
16
|
+
@typing.overload
|
|
17
|
+
def start_word_to_pdf(file_path: str, output_path: str, callback: ConvertCallback | None = None) -> ErrorCode:
|
|
18
|
+
"""
|
|
19
|
+
Converts a DOCX document to PDF with the default options.
|
|
20
|
+
"""
|
|
21
|
+
@staticmethod
|
|
22
|
+
@typing.overload
|
|
23
|
+
def start_word_to_pdf(file_path: str, output_path: str, options: ConvertOptions = ..., callback: ConvertCallback | None = None) -> ErrorCode:
|
|
24
|
+
"""
|
|
25
|
+
Converts a DOCX document to PDF. Only options.page_ranges and options.word_pdf_bookmark_mode take effect; the other options do not apply.
|
|
26
|
+
"""
|
|
27
|
+
@staticmethod
|
|
28
|
+
def start_pdf_to_excel(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
29
|
+
"""
|
|
30
|
+
Starts the conversion of a PDF file to an Excel document.
|
|
31
|
+
"""
|
|
32
|
+
@staticmethod
|
|
33
|
+
def start_pdf_to_html(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
34
|
+
"""
|
|
35
|
+
Starts the conversion of a PDF file to an HTML document.
|
|
36
|
+
"""
|
|
37
|
+
@staticmethod
|
|
38
|
+
def start_pdf_to_image(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
39
|
+
"""
|
|
40
|
+
Starts the conversion of a PDF file to an image format.
|
|
41
|
+
"""
|
|
42
|
+
@staticmethod
|
|
43
|
+
def start_pdf_to_json(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
44
|
+
"""
|
|
45
|
+
Starts the conversion of a PDF file to a JSON document.
|
|
46
|
+
"""
|
|
47
|
+
@staticmethod
|
|
48
|
+
def start_pdf_to_markdown(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
49
|
+
"""
|
|
50
|
+
Starts the conversion of a PDF file to a Markdown document.
|
|
51
|
+
"""
|
|
52
|
+
@staticmethod
|
|
53
|
+
def start_pdf_to_ofd(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
54
|
+
"""
|
|
55
|
+
Starts the conversion of a PDF file to an OFD document.
|
|
56
|
+
"""
|
|
57
|
+
@staticmethod
|
|
58
|
+
def start_pdf_to_ppt(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
59
|
+
"""
|
|
60
|
+
Starts the conversion of a PDF file to a PowerPoint presentation.
|
|
61
|
+
"""
|
|
62
|
+
@staticmethod
|
|
63
|
+
def start_pdf_to_rtf(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
64
|
+
"""
|
|
65
|
+
Starts the conversion of a PDF file to an RTF document.
|
|
66
|
+
"""
|
|
67
|
+
@staticmethod
|
|
68
|
+
def start_pdf_to_searchable_pdf(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
69
|
+
"""
|
|
70
|
+
Starts the conversion of a PDF file to a searchable PDF document.
|
|
71
|
+
"""
|
|
72
|
+
@staticmethod
|
|
73
|
+
def start_pdf_to_txt(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
74
|
+
"""
|
|
75
|
+
Starts the conversion of a PDF file to a plain text file.
|
|
76
|
+
"""
|
|
77
|
+
@staticmethod
|
|
78
|
+
def start_pdf_to_word(file_path: str, password: str, output_path: str, options: ConvertOptions, callback: ConvertCallback = None) -> ErrorCode:
|
|
79
|
+
"""
|
|
80
|
+
Starts the conversion of a PDF file to a Word document.
|
|
81
|
+
"""
|
|
82
|
+
class ConvertCallback:
|
|
83
|
+
"""
|
|
84
|
+
Callback bundle for conversion progress and cancellation. Each instance maintains its own callback state.
|
|
85
|
+
"""
|
|
86
|
+
def __init__(self) -> None:
|
|
87
|
+
"""
|
|
88
|
+
Default constructor
|
|
89
|
+
"""
|
|
90
|
+
def reset(self) -> None:
|
|
91
|
+
"""
|
|
92
|
+
Resets all callbacks to None.
|
|
93
|
+
"""
|
|
94
|
+
def set_cancel(self, cancel: collections.abc.Callable[[], bool]) -> None:
|
|
95
|
+
"""
|
|
96
|
+
Sets a callback function for cancellation check. Return True to cancel the conversion.
|
|
97
|
+
"""
|
|
98
|
+
def set_progress(self, progress: collections.abc.Callable[[typing.SupportsInt | typing.SupportsIndex, typing.SupportsInt | typing.SupportsIndex], None]) -> None:
|
|
99
|
+
"""
|
|
100
|
+
Sets a callback function to track the progress of conversion. The callback receives (current_page, total_page).
|
|
101
|
+
"""
|
|
102
|
+
def set_ocr(self, ocr: collections.abc.Callable[[str], bool]) -> None:
|
|
103
|
+
"""
|
|
104
|
+
Sets a trigger callback for external OCR. Receives image path, returns True on success.
|
|
105
|
+
"""
|
|
106
|
+
def set_layout(self, layout: collections.abc.Callable[[str], bool]) -> None:
|
|
107
|
+
"""
|
|
108
|
+
Sets a trigger callback for external layout analysis. Receives image path, returns True on success.
|
|
109
|
+
"""
|
|
110
|
+
def set_table(self, table: collections.abc.Callable[[str], bool]) -> None:
|
|
111
|
+
"""
|
|
112
|
+
Sets a trigger callback for external table recognition. Receives image path, returns True on success.
|
|
113
|
+
"""
|
|
114
|
+
def set_get_ocr_result(self, get_ocr_result: collections.abc.Callable[[], str]) -> None:
|
|
115
|
+
"""
|
|
116
|
+
Sets a getter callback to retrieve OCR result as a JSON string.
|
|
117
|
+
"""
|
|
118
|
+
def set_get_layout_result(self, get_layout_result: collections.abc.Callable[[], str]) -> None:
|
|
119
|
+
"""
|
|
120
|
+
Sets a getter callback to retrieve layout analysis result as a JSON string.
|
|
121
|
+
"""
|
|
122
|
+
def set_get_table_result(self, get_table_result: collections.abc.Callable[[], str]) -> None:
|
|
123
|
+
"""
|
|
124
|
+
Sets a getter callback to retrieve table recognition result as a JSON string.
|
|
125
|
+
"""
|
|
126
|
+
class ConvertOptions:
|
|
127
|
+
def __init__(self) -> None:
|
|
128
|
+
"""
|
|
129
|
+
Default constructor
|
|
130
|
+
"""
|
|
131
|
+
def __repr__(self) -> str:
|
|
132
|
+
"""
|
|
133
|
+
String representation of ConvertOptions object
|
|
134
|
+
"""
|
|
135
|
+
def __str__(self) -> str:
|
|
136
|
+
"""
|
|
137
|
+
String representation of ConvertOptions object
|
|
138
|
+
"""
|
|
139
|
+
@property
|
|
140
|
+
def auto_create_folder(self) -> bool:
|
|
141
|
+
"""
|
|
142
|
+
Whether to automatically create folder when exporting multiple documents
|
|
143
|
+
"""
|
|
144
|
+
@auto_create_folder.setter
|
|
145
|
+
def auto_create_folder(self, arg0: bool) -> None:
|
|
146
|
+
...
|
|
147
|
+
@property
|
|
148
|
+
def contain_annotation(self) -> bool:
|
|
149
|
+
"""
|
|
150
|
+
Whether to contain annotations when converting
|
|
151
|
+
"""
|
|
152
|
+
@contain_annotation.setter
|
|
153
|
+
def contain_annotation(self, arg0: bool) -> None:
|
|
154
|
+
...
|
|
155
|
+
@property
|
|
156
|
+
def contain_image(self) -> bool:
|
|
157
|
+
"""
|
|
158
|
+
Whether to contain images when converting, which takes effect only when enable_ocr is false
|
|
159
|
+
"""
|
|
160
|
+
@contain_image.setter
|
|
161
|
+
def contain_image(self, arg0: bool) -> None:
|
|
162
|
+
...
|
|
163
|
+
@property
|
|
164
|
+
def contain_page_background_image(self) -> bool:
|
|
165
|
+
"""
|
|
166
|
+
Whether to contain page background images when converting,which takes effect only when enable_ocr is true.
|
|
167
|
+
"""
|
|
168
|
+
@contain_page_background_image.setter
|
|
169
|
+
def contain_page_background_image(self, arg0: bool) -> None:
|
|
170
|
+
...
|
|
171
|
+
@property
|
|
172
|
+
def enable_ai_layout(self) -> bool:
|
|
173
|
+
"""
|
|
174
|
+
Whether to enable AI layout analysis during conversion
|
|
175
|
+
"""
|
|
176
|
+
@enable_ai_layout.setter
|
|
177
|
+
def enable_ai_layout(self, arg0: bool) -> None:
|
|
178
|
+
...
|
|
179
|
+
@property
|
|
180
|
+
def enable_ai_table_recognition(self) -> bool:
|
|
181
|
+
"""
|
|
182
|
+
Whether to enable AI table recognition during conversion
|
|
183
|
+
"""
|
|
184
|
+
@enable_ai_table_recognition.setter
|
|
185
|
+
def enable_ai_table_recognition(self, arg0: bool) -> None:
|
|
186
|
+
...
|
|
187
|
+
@property
|
|
188
|
+
def table_recognition_accuracy(self) -> TableRecognitionAccuracy:
|
|
189
|
+
"""
|
|
190
|
+
DocumentAI table recognition accuracy
|
|
191
|
+
"""
|
|
192
|
+
@table_recognition_accuracy.setter
|
|
193
|
+
def table_recognition_accuracy(self, arg0: TableRecognitionAccuracy) -> None:
|
|
194
|
+
...
|
|
195
|
+
@property
|
|
196
|
+
def enable_ocr(self) -> bool:
|
|
197
|
+
"""
|
|
198
|
+
Whether to use OCR
|
|
199
|
+
"""
|
|
200
|
+
@enable_ocr.setter
|
|
201
|
+
def enable_ocr(self, arg0: bool) -> None:
|
|
202
|
+
...
|
|
203
|
+
@property
|
|
204
|
+
def enable_auto_page_size(self) -> bool:
|
|
205
|
+
"""
|
|
206
|
+
Whether to size the output page from the image's own resolution, matching it to the nearest standard paper. Only takes effect when the input is an image file
|
|
207
|
+
"""
|
|
208
|
+
@enable_auto_page_size.setter
|
|
209
|
+
def enable_auto_page_size(self, arg0: bool) -> None:
|
|
210
|
+
...
|
|
211
|
+
@property
|
|
212
|
+
def custom_page_height(self) -> float:
|
|
213
|
+
"""
|
|
214
|
+
Output page height in points for image input
|
|
215
|
+
"""
|
|
216
|
+
@custom_page_height.setter
|
|
217
|
+
def custom_page_height(self, arg0: float) -> None:
|
|
218
|
+
...
|
|
219
|
+
@property
|
|
220
|
+
def custom_page_width(self) -> float:
|
|
221
|
+
"""
|
|
222
|
+
Output page width in points for image input; set with custom_page_height to choose the page outright
|
|
223
|
+
"""
|
|
224
|
+
@custom_page_width.setter
|
|
225
|
+
def custom_page_width(self, arg0: float) -> None:
|
|
226
|
+
...
|
|
227
|
+
@property
|
|
228
|
+
def enable_document_dewarp(self) -> bool:
|
|
229
|
+
"""
|
|
230
|
+
Whether to apply DocumentAI dewarp before OCR image recognition
|
|
231
|
+
"""
|
|
232
|
+
@enable_document_dewarp.setter
|
|
233
|
+
def enable_document_dewarp(self, arg0: bool) -> None:
|
|
234
|
+
...
|
|
235
|
+
@property
|
|
236
|
+
def enable_document_orientation_classification(self) -> bool:
|
|
237
|
+
"""
|
|
238
|
+
Whether to classify and correct document orientation before OCR image recognition
|
|
239
|
+
"""
|
|
240
|
+
@enable_document_orientation_classification.setter
|
|
241
|
+
def enable_document_orientation_classification(self, arg0: bool) -> None:
|
|
242
|
+
...
|
|
243
|
+
@property
|
|
244
|
+
def excel_all_content(self) -> bool:
|
|
245
|
+
"""
|
|
246
|
+
Whether to set contain all pdf content to the xlsx file
|
|
247
|
+
"""
|
|
248
|
+
@excel_all_content.setter
|
|
249
|
+
def excel_all_content(self, arg0: bool) -> None:
|
|
250
|
+
...
|
|
251
|
+
@property
|
|
252
|
+
def excel_csv_format(self) -> bool:
|
|
253
|
+
"""
|
|
254
|
+
Whether to set to save the table in csv format
|
|
255
|
+
"""
|
|
256
|
+
@excel_csv_format.setter
|
|
257
|
+
def excel_csv_format(self, arg0: bool) -> None:
|
|
258
|
+
...
|
|
259
|
+
@property
|
|
260
|
+
def excel_worksheet_option(self) -> ExcelWorksheetOption:
|
|
261
|
+
"""
|
|
262
|
+
Specify the Excel worksheet option for conversion
|
|
263
|
+
"""
|
|
264
|
+
@excel_worksheet_option.setter
|
|
265
|
+
def excel_worksheet_option(self, arg0: ExcelWorksheetOption) -> None:
|
|
266
|
+
...
|
|
267
|
+
@property
|
|
268
|
+
def font_name(self) -> str:
|
|
269
|
+
"""
|
|
270
|
+
Specify the fontname to convert, e.g. "Arial"
|
|
271
|
+
"""
|
|
272
|
+
@font_name.setter
|
|
273
|
+
def font_name(self, arg0: str) -> None:
|
|
274
|
+
...
|
|
275
|
+
@property
|
|
276
|
+
def formula_to_image(self) -> bool:
|
|
277
|
+
"""
|
|
278
|
+
Whether to convert formula to image
|
|
279
|
+
"""
|
|
280
|
+
@formula_to_image.setter
|
|
281
|
+
def formula_to_image(self, arg0: bool) -> None:
|
|
282
|
+
...
|
|
283
|
+
@property
|
|
284
|
+
def html_option(self) -> HtmlOption:
|
|
285
|
+
"""
|
|
286
|
+
Specify the HTML option for conversion
|
|
287
|
+
"""
|
|
288
|
+
@html_option.setter
|
|
289
|
+
def html_option(self, arg0: HtmlOption) -> None:
|
|
290
|
+
...
|
|
291
|
+
@property
|
|
292
|
+
def image_color_mode(self) -> ImageColorMode:
|
|
293
|
+
"""
|
|
294
|
+
Specify the image color mode of the image file
|
|
295
|
+
"""
|
|
296
|
+
@image_color_mode.setter
|
|
297
|
+
def image_color_mode(self, arg0: ImageColorMode) -> None:
|
|
298
|
+
...
|
|
299
|
+
@property
|
|
300
|
+
def image_path_enhance(self) -> bool:
|
|
301
|
+
"""
|
|
302
|
+
Whether to enhance the image path
|
|
303
|
+
"""
|
|
304
|
+
@image_path_enhance.setter
|
|
305
|
+
def image_path_enhance(self, arg0: bool) -> None:
|
|
306
|
+
...
|
|
307
|
+
@property
|
|
308
|
+
def image_scaling(self) -> float:
|
|
309
|
+
"""
|
|
310
|
+
Specify the image scaling of the image file
|
|
311
|
+
"""
|
|
312
|
+
@image_scaling.setter
|
|
313
|
+
def image_scaling(self, arg0: typing.SupportsFloat | typing.SupportsIndex) -> None:
|
|
314
|
+
...
|
|
315
|
+
@property
|
|
316
|
+
def image_type(self) -> ImageType:
|
|
317
|
+
"""
|
|
318
|
+
Specify the image type of the image file
|
|
319
|
+
"""
|
|
320
|
+
@image_type.setter
|
|
321
|
+
def image_type(self, arg0: ImageType) -> None:
|
|
322
|
+
...
|
|
323
|
+
@property
|
|
324
|
+
def json_contain_table(self) -> bool:
|
|
325
|
+
"""
|
|
326
|
+
Whether to contain table when convert pdf to json
|
|
327
|
+
"""
|
|
328
|
+
@json_contain_table.setter
|
|
329
|
+
def json_contain_table(self, arg0: bool) -> None:
|
|
330
|
+
...
|
|
331
|
+
@property
|
|
332
|
+
def languages(self) -> list[OCRLanguage]:
|
|
333
|
+
"""
|
|
334
|
+
Specify the OCR languages
|
|
335
|
+
"""
|
|
336
|
+
@languages.setter
|
|
337
|
+
def languages(self, arg0: list[OCRLanguage]) -> None:
|
|
338
|
+
...
|
|
339
|
+
@property
|
|
340
|
+
def ocr_option(self) -> OCROption:
|
|
341
|
+
"""
|
|
342
|
+
Specify the OCR option
|
|
343
|
+
"""
|
|
344
|
+
@ocr_option.setter
|
|
345
|
+
def ocr_option(self, arg0: OCROption) -> None:
|
|
346
|
+
...
|
|
347
|
+
@property
|
|
348
|
+
def output_document_per_page(self) -> bool:
|
|
349
|
+
"""
|
|
350
|
+
whether to output one document per page
|
|
351
|
+
"""
|
|
352
|
+
@output_document_per_page.setter
|
|
353
|
+
def output_document_per_page(self, arg0: bool) -> None:
|
|
354
|
+
...
|
|
355
|
+
@property
|
|
356
|
+
def page_layout_mode(self) -> PageLayoutMode:
|
|
357
|
+
"""
|
|
358
|
+
Specify the layout mode
|
|
359
|
+
"""
|
|
360
|
+
@page_layout_mode.setter
|
|
361
|
+
def page_layout_mode(self, arg0: PageLayoutMode) -> None:
|
|
362
|
+
...
|
|
363
|
+
@property
|
|
364
|
+
def page_ranges(self) -> str:
|
|
365
|
+
"""
|
|
366
|
+
Specify the pages to convert, e.g. "1-3,5,7-9"
|
|
367
|
+
"""
|
|
368
|
+
@page_ranges.setter
|
|
369
|
+
def page_ranges(self, arg0: str) -> None:
|
|
370
|
+
...
|
|
371
|
+
@property
|
|
372
|
+
def transparent_text(self) -> bool:
|
|
373
|
+
"""
|
|
374
|
+
Whether to make the text transparent in the output document
|
|
375
|
+
"""
|
|
376
|
+
@transparent_text.setter
|
|
377
|
+
def transparent_text(self, arg0: bool) -> None:
|
|
378
|
+
...
|
|
379
|
+
@property
|
|
380
|
+
def txt_table_format(self) -> bool:
|
|
381
|
+
"""
|
|
382
|
+
Whether format table when convert pdf to txt
|
|
383
|
+
"""
|
|
384
|
+
@txt_table_format.setter
|
|
385
|
+
def txt_table_format(self, arg0: bool) -> None:
|
|
386
|
+
...
|
|
387
|
+
@property
|
|
388
|
+
def word_pdf_bookmark_mode(self) -> WordPdfBookmarkMode:
|
|
389
|
+
"""
|
|
390
|
+
How the PDF bookmarks are generated. Only takes effect for Word to PDF
|
|
391
|
+
"""
|
|
392
|
+
@word_pdf_bookmark_mode.setter
|
|
393
|
+
def word_pdf_bookmark_mode(self, arg0: WordPdfBookmarkMode) -> None:
|
|
394
|
+
...
|
|
395
|
+
class ErrorCode:
|
|
396
|
+
"""
|
|
397
|
+
Members:
|
|
398
|
+
|
|
399
|
+
SUCCESS : Success, and no error occurs
|
|
400
|
+
|
|
401
|
+
CANCEL : Conversion process was canceled
|
|
402
|
+
|
|
403
|
+
FILE_ERROR : File cannot be found or could not be opened
|
|
404
|
+
|
|
405
|
+
PDF_PASSWORD_ERROR : Invalid password. Usually, this error may occur when loading a PDF document with password. When meet this, user should load document again with correct password
|
|
406
|
+
|
|
407
|
+
PDF_PAGE_ERROR : PDF page failed to load
|
|
408
|
+
|
|
409
|
+
PDF_FORMAT_ERROR : Format is invalid. For files, this may also mean that file is corrupted
|
|
410
|
+
|
|
411
|
+
PDF_SECURITY_ERROR : PDF document is encrypted by some unsupported security handler
|
|
412
|
+
|
|
413
|
+
OUT_OF_MEMORY : Out-of-memory error occurs
|
|
414
|
+
|
|
415
|
+
IO_ERROR : System I/O error
|
|
416
|
+
|
|
417
|
+
COMPRESS_ERROR : Folder compression failed
|
|
418
|
+
|
|
419
|
+
LICENSE_INVALID : The license is invalid
|
|
420
|
+
|
|
421
|
+
LICENSE_EXPIRE : The license has expired
|
|
422
|
+
|
|
423
|
+
LICENSE_UNSUPPORTED_PLATFORM : The license does not support the current platform
|
|
424
|
+
|
|
425
|
+
LICENSE_UNSUPPORTED_ID : The license does not support the application id
|
|
426
|
+
|
|
427
|
+
LICENSE_UNSUPPORTED_DEVICE : The license does not support the device id
|
|
428
|
+
|
|
429
|
+
LICENSE_PERMISSION_DENY : The license does not have the function permission
|
|
430
|
+
|
|
431
|
+
LICENSE_UNINITIALIZED : The license has not been initialized
|
|
432
|
+
|
|
433
|
+
LICENSE_ILLEGAL_ACCESS : Illegal access to the API interface
|
|
434
|
+
|
|
435
|
+
LICENSE_FILE_READ_FAILED : Failed to read license file
|
|
436
|
+
|
|
437
|
+
LICENSE_OCR_PERMISSION_DENY : The license does not have OCR permissions
|
|
438
|
+
|
|
439
|
+
LICENSE_CONCURRENCY_EXCEEDED : The current conversion concurrency exceeds the license limit
|
|
440
|
+
|
|
441
|
+
LICENSE_PAGE_LIMIT_EXCEEDED : The current conversion pages exceed the license limit
|
|
442
|
+
|
|
443
|
+
LICENSE_QUOTA_CORRUPTED : The quota persistence file has been tampered with
|
|
444
|
+
|
|
445
|
+
NO_TABLE_ERROR : No tables found in the source file
|
|
446
|
+
|
|
447
|
+
OCR_FAILURE : Failed to call OCR recognition
|
|
448
|
+
|
|
449
|
+
CONVERTING_ERROR : Currently executing conversion task
|
|
450
|
+
|
|
451
|
+
INVALID_ARG : Invalid argument provided
|
|
452
|
+
|
|
453
|
+
INVALID_HANDLE : The handle is invalid, possibly uninitialized or already released
|
|
454
|
+
|
|
455
|
+
INVALID_MODEL_FORMAT : The model file format is invalid or corrupted
|
|
456
|
+
|
|
457
|
+
MODEL_FUNCTION_UNSUPPORTED : The model does not support the requested function or operation
|
|
458
|
+
|
|
459
|
+
MODEL_FORMAT_UNSUPPORTED : The model format is not supported by this system or SDK
|
|
460
|
+
|
|
461
|
+
MODEL_SDK_MISMATCH : The model is incompatible with the current SDK version
|
|
462
|
+
|
|
463
|
+
IMAGE_DATA_EMPTY : The image data is empty or not provided
|
|
464
|
+
|
|
465
|
+
IMAGE_WIDTH_HEIGHT_ERROR : The image width or height is invalid (e.g., less than or equal to zero)
|
|
466
|
+
|
|
467
|
+
IMAGE_FORMAT_UNSUPPORTED : The image format is not supported (e.g., not RGB, YUV, etc.)
|
|
468
|
+
|
|
469
|
+
IMAGE_INVALID : The image is invalid or corrupted
|
|
470
|
+
|
|
471
|
+
EXPIRE_ERROR : The resource (e.g., license, token) has expired
|
|
472
|
+
|
|
473
|
+
MISSING_ARG : A required argument is missing
|
|
474
|
+
|
|
475
|
+
LICENSE_UNSUPPORTED_API : The current license does not support calling this API
|
|
476
|
+
|
|
477
|
+
LICENSE_MISMATCH : The license does not match the device, module, or version
|
|
478
|
+
|
|
479
|
+
INVALID_TABLE : The table data is invalid or null
|
|
480
|
+
|
|
481
|
+
UNSUPPORTED_FEATURE : The source document uses a feature this SDK cannot fully reproduce, or the requested output cannot carry the input's content; a usable output may still have been written
|
|
482
|
+
|
|
483
|
+
UNKNOWN_ERROR : Unknown error
|
|
484
|
+
"""
|
|
485
|
+
CANCEL: typing.ClassVar[ErrorCode] # value = <ErrorCode.CANCEL: 1>
|
|
486
|
+
COMPRESS_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.COMPRESS_ERROR: 9>
|
|
487
|
+
CONVERTING_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.CONVERTING_ERROR: 60>
|
|
488
|
+
EXPIRE_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.EXPIRE_ERROR: 90>
|
|
489
|
+
FILE_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.FILE_ERROR: 2>
|
|
490
|
+
IMAGE_DATA_EMPTY: typing.ClassVar[ErrorCode] # value = <ErrorCode.IMAGE_DATA_EMPTY: 86>
|
|
491
|
+
IMAGE_FORMAT_UNSUPPORTED: typing.ClassVar[ErrorCode] # value = <ErrorCode.IMAGE_FORMAT_UNSUPPORTED: 88>
|
|
492
|
+
IMAGE_INVALID: typing.ClassVar[ErrorCode] # value = <ErrorCode.IMAGE_INVALID: 89>
|
|
493
|
+
IMAGE_WIDTH_HEIGHT_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.IMAGE_WIDTH_HEIGHT_ERROR: 87>
|
|
494
|
+
INVALID_ARG: typing.ClassVar[ErrorCode] # value = <ErrorCode.INVALID_ARG: 80>
|
|
495
|
+
INVALID_HANDLE: typing.ClassVar[ErrorCode] # value = <ErrorCode.INVALID_HANDLE: 81>
|
|
496
|
+
INVALID_MODEL_FORMAT: typing.ClassVar[ErrorCode] # value = <ErrorCode.INVALID_MODEL_FORMAT: 82>
|
|
497
|
+
INVALID_TABLE: typing.ClassVar[ErrorCode] # value = <ErrorCode.INVALID_TABLE: 94>
|
|
498
|
+
IO_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.IO_ERROR: 8>
|
|
499
|
+
LICENSE_CONCURRENCY_EXCEEDED: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_CONCURRENCY_EXCEEDED: 30>
|
|
500
|
+
LICENSE_EXPIRE: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_EXPIRE: 21>
|
|
501
|
+
LICENSE_FILE_READ_FAILED: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_FILE_READ_FAILED: 28>
|
|
502
|
+
LICENSE_ILLEGAL_ACCESS: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_ILLEGAL_ACCESS: 27>
|
|
503
|
+
LICENSE_INVALID: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_INVALID: 20>
|
|
504
|
+
LICENSE_MISMATCH: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_MISMATCH: 93>
|
|
505
|
+
LICENSE_OCR_PERMISSION_DENY: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_OCR_PERMISSION_DENY: 29>
|
|
506
|
+
LICENSE_PAGE_LIMIT_EXCEEDED: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_PAGE_LIMIT_EXCEEDED: 31>
|
|
507
|
+
LICENSE_PERMISSION_DENY: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_PERMISSION_DENY: 25>
|
|
508
|
+
LICENSE_QUOTA_CORRUPTED: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_QUOTA_CORRUPTED: 32>
|
|
509
|
+
LICENSE_UNINITIALIZED: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_UNINITIALIZED: 26>
|
|
510
|
+
LICENSE_UNSUPPORTED_API: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_UNSUPPORTED_API: 92>
|
|
511
|
+
LICENSE_UNSUPPORTED_DEVICE: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_UNSUPPORTED_DEVICE: 24>
|
|
512
|
+
LICENSE_UNSUPPORTED_ID: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_UNSUPPORTED_ID: 23>
|
|
513
|
+
LICENSE_UNSUPPORTED_PLATFORM: typing.ClassVar[ErrorCode] # value = <ErrorCode.LICENSE_UNSUPPORTED_PLATFORM: 22>
|
|
514
|
+
MISSING_ARG: typing.ClassVar[ErrorCode] # value = <ErrorCode.MISSING_ARG: 91>
|
|
515
|
+
MODEL_FORMAT_UNSUPPORTED: typing.ClassVar[ErrorCode] # value = <ErrorCode.MODEL_FORMAT_UNSUPPORTED: 84>
|
|
516
|
+
MODEL_FUNCTION_UNSUPPORTED: typing.ClassVar[ErrorCode] # value = <ErrorCode.MODEL_FUNCTION_UNSUPPORTED: 83>
|
|
517
|
+
MODEL_SDK_MISMATCH: typing.ClassVar[ErrorCode] # value = <ErrorCode.MODEL_SDK_MISMATCH: 85>
|
|
518
|
+
NO_TABLE_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.NO_TABLE_ERROR: 40>
|
|
519
|
+
OCR_FAILURE: typing.ClassVar[ErrorCode] # value = <ErrorCode.OCR_FAILURE: 41>
|
|
520
|
+
OUT_OF_MEMORY: typing.ClassVar[ErrorCode] # value = <ErrorCode.OUT_OF_MEMORY: 7>
|
|
521
|
+
PDF_FORMAT_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.PDF_FORMAT_ERROR: 5>
|
|
522
|
+
PDF_PAGE_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.PDF_PAGE_ERROR: 4>
|
|
523
|
+
PDF_PASSWORD_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.PDF_PASSWORD_ERROR: 3>
|
|
524
|
+
PDF_SECURITY_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.PDF_SECURITY_ERROR: 6>
|
|
525
|
+
SUCCESS: typing.ClassVar[ErrorCode] # value = <ErrorCode.SUCCESS: 0>
|
|
526
|
+
UNKNOWN_ERROR: typing.ClassVar[ErrorCode] # value = <ErrorCode.UNKNOWN_ERROR: 100>
|
|
527
|
+
UNSUPPORTED_FEATURE: typing.ClassVar[ErrorCode] # value = <ErrorCode.UNSUPPORTED_FEATURE: 95>
|
|
528
|
+
__members__: typing.ClassVar[dict[str, ErrorCode]] # value = {'SUCCESS': <ErrorCode.SUCCESS: 0>, 'CANCEL': <ErrorCode.CANCEL: 1>, 'FILE_ERROR': <ErrorCode.FILE_ERROR: 2>, 'PDF_PASSWORD_ERROR': <ErrorCode.PDF_PASSWORD_ERROR: 3>, 'PDF_PAGE_ERROR': <ErrorCode.PDF_PAGE_ERROR: 4>, 'PDF_FORMAT_ERROR': <ErrorCode.PDF_FORMAT_ERROR: 5>, 'PDF_SECURITY_ERROR': <ErrorCode.PDF_SECURITY_ERROR: 6>, 'OUT_OF_MEMORY': <ErrorCode.OUT_OF_MEMORY: 7>, 'IO_ERROR': <ErrorCode.IO_ERROR: 8>, 'COMPRESS_ERROR': <ErrorCode.COMPRESS_ERROR: 9>, 'LICENSE_INVALID': <ErrorCode.LICENSE_INVALID: 20>, 'LICENSE_EXPIRE': <ErrorCode.LICENSE_EXPIRE: 21>, 'LICENSE_UNSUPPORTED_PLATFORM': <ErrorCode.LICENSE_UNSUPPORTED_PLATFORM: 22>, 'LICENSE_UNSUPPORTED_ID': <ErrorCode.LICENSE_UNSUPPORTED_ID: 23>, 'LICENSE_UNSUPPORTED_DEVICE': <ErrorCode.LICENSE_UNSUPPORTED_DEVICE: 24>, 'LICENSE_PERMISSION_DENY': <ErrorCode.LICENSE_PERMISSION_DENY: 25>, 'LICENSE_UNINITIALIZED': <ErrorCode.LICENSE_UNINITIALIZED: 26>, 'LICENSE_ILLEGAL_ACCESS': <ErrorCode.LICENSE_ILLEGAL_ACCESS: 27>, 'LICENSE_FILE_READ_FAILED': <ErrorCode.LICENSE_FILE_READ_FAILED: 28>, 'LICENSE_OCR_PERMISSION_DENY': <ErrorCode.LICENSE_OCR_PERMISSION_DENY: 29>, 'LICENSE_CONCURRENCY_EXCEEDED': <ErrorCode.LICENSE_CONCURRENCY_EXCEEDED: 30>, 'LICENSE_PAGE_LIMIT_EXCEEDED': <ErrorCode.LICENSE_PAGE_LIMIT_EXCEEDED: 31>, 'LICENSE_QUOTA_CORRUPTED': <ErrorCode.LICENSE_QUOTA_CORRUPTED: 32>, 'NO_TABLE_ERROR': <ErrorCode.NO_TABLE_ERROR: 40>, 'OCR_FAILURE': <ErrorCode.OCR_FAILURE: 41>, 'CONVERTING_ERROR': <ErrorCode.CONVERTING_ERROR: 60>, 'INVALID_ARG': <ErrorCode.INVALID_ARG: 80>, 'INVALID_HANDLE': <ErrorCode.INVALID_HANDLE: 81>, 'INVALID_MODEL_FORMAT': <ErrorCode.INVALID_MODEL_FORMAT: 82>, 'MODEL_FUNCTION_UNSUPPORTED': <ErrorCode.MODEL_FUNCTION_UNSUPPORTED: 83>, 'MODEL_FORMAT_UNSUPPORTED': <ErrorCode.MODEL_FORMAT_UNSUPPORTED: 84>, 'MODEL_SDK_MISMATCH': <ErrorCode.MODEL_SDK_MISMATCH: 85>, 'IMAGE_DATA_EMPTY': <ErrorCode.IMAGE_DATA_EMPTY: 86>, 'IMAGE_WIDTH_HEIGHT_ERROR': <ErrorCode.IMAGE_WIDTH_HEIGHT_ERROR: 87>, 'IMAGE_FORMAT_UNSUPPORTED': <ErrorCode.IMAGE_FORMAT_UNSUPPORTED: 88>, 'IMAGE_INVALID': <ErrorCode.IMAGE_INVALID: 89>, 'EXPIRE_ERROR': <ErrorCode.EXPIRE_ERROR: 90>, 'MISSING_ARG': <ErrorCode.MISSING_ARG: 91>, 'LICENSE_UNSUPPORTED_API': <ErrorCode.LICENSE_UNSUPPORTED_API: 92>, 'LICENSE_MISMATCH': <ErrorCode.LICENSE_MISMATCH: 93>, 'INVALID_TABLE': <ErrorCode.INVALID_TABLE: 94>, 'UNSUPPORTED_FEATURE': <ErrorCode.UNSUPPORTED_FEATURE: 95>, 'UNKNOWN_ERROR': <ErrorCode.UNKNOWN_ERROR: 100>}
|
|
529
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
530
|
+
...
|
|
531
|
+
def __getstate__(self) -> int:
|
|
532
|
+
...
|
|
533
|
+
def __hash__(self) -> int:
|
|
534
|
+
...
|
|
535
|
+
def __index__(self) -> int:
|
|
536
|
+
...
|
|
537
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
538
|
+
...
|
|
539
|
+
def __int__(self) -> int:
|
|
540
|
+
...
|
|
541
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
542
|
+
...
|
|
543
|
+
def __repr__(self) -> str:
|
|
544
|
+
...
|
|
545
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
546
|
+
...
|
|
547
|
+
def __str__(self) -> str:
|
|
548
|
+
...
|
|
549
|
+
@property
|
|
550
|
+
def name(self) -> str:
|
|
551
|
+
...
|
|
552
|
+
@property
|
|
553
|
+
def value(self) -> int:
|
|
554
|
+
...
|
|
555
|
+
class TableRecognitionAccuracy:
|
|
556
|
+
"""
|
|
557
|
+
DocumentAI table recognition model profile.
|
|
558
|
+
|
|
559
|
+
Members:
|
|
560
|
+
|
|
561
|
+
HIGH_ACCURACY : Prioritize recognition accuracy; may use more resources
|
|
562
|
+
|
|
563
|
+
BALANCED : Balanced recognition accuracy, resource usage, and throughput
|
|
564
|
+
"""
|
|
565
|
+
HIGH_ACCURACY: typing.ClassVar[TableRecognitionAccuracy]
|
|
566
|
+
BALANCED: typing.ClassVar[TableRecognitionAccuracy]
|
|
567
|
+
__members__: typing.ClassVar[dict[str, TableRecognitionAccuracy]]
|
|
568
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None: ...
|
|
569
|
+
def __eq__(self, other: typing.Any) -> bool: ...
|
|
570
|
+
def __hash__(self) -> int: ...
|
|
571
|
+
def __index__(self) -> int: ...
|
|
572
|
+
def __int__(self) -> int: ...
|
|
573
|
+
@property
|
|
574
|
+
def name(self) -> str: ...
|
|
575
|
+
@property
|
|
576
|
+
def value(self) -> int: ...
|
|
577
|
+
HIGH_ACCURACY: TableRecognitionAccuracy
|
|
578
|
+
BALANCED: TableRecognitionAccuracy
|
|
579
|
+
class ExcelWorksheetOption:
|
|
580
|
+
"""
|
|
581
|
+
Members:
|
|
582
|
+
|
|
583
|
+
FOR_TABLE : A worksheet to contain only one table
|
|
584
|
+
|
|
585
|
+
FOR_PAGE : A worksheet to contain table for PDF Page
|
|
586
|
+
|
|
587
|
+
FOR_DOCUMENT : A worksheet to contain table for PDF Document
|
|
588
|
+
"""
|
|
589
|
+
FOR_DOCUMENT: typing.ClassVar[ExcelWorksheetOption] # value = <ExcelWorksheetOption.FOR_DOCUMENT: 2>
|
|
590
|
+
FOR_PAGE: typing.ClassVar[ExcelWorksheetOption] # value = <ExcelWorksheetOption.FOR_PAGE: 1>
|
|
591
|
+
FOR_TABLE: typing.ClassVar[ExcelWorksheetOption] # value = <ExcelWorksheetOption.FOR_TABLE: 0>
|
|
592
|
+
__members__: typing.ClassVar[dict[str, ExcelWorksheetOption]] # value = {'FOR_TABLE': <ExcelWorksheetOption.FOR_TABLE: 0>, 'FOR_PAGE': <ExcelWorksheetOption.FOR_PAGE: 1>, 'FOR_DOCUMENT': <ExcelWorksheetOption.FOR_DOCUMENT: 2>}
|
|
593
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
594
|
+
...
|
|
595
|
+
def __getstate__(self) -> int:
|
|
596
|
+
...
|
|
597
|
+
def __hash__(self) -> int:
|
|
598
|
+
...
|
|
599
|
+
def __index__(self) -> int:
|
|
600
|
+
...
|
|
601
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
602
|
+
...
|
|
603
|
+
def __int__(self) -> int:
|
|
604
|
+
...
|
|
605
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
606
|
+
...
|
|
607
|
+
def __repr__(self) -> str:
|
|
608
|
+
...
|
|
609
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
610
|
+
...
|
|
611
|
+
def __str__(self) -> str:
|
|
612
|
+
...
|
|
613
|
+
@property
|
|
614
|
+
def name(self) -> str:
|
|
615
|
+
...
|
|
616
|
+
@property
|
|
617
|
+
def value(self) -> int:
|
|
618
|
+
...
|
|
619
|
+
class HtmlOption:
|
|
620
|
+
"""
|
|
621
|
+
Members:
|
|
622
|
+
|
|
623
|
+
SINGLE_PAGE : Convert the entire PDF file into a single HTML file
|
|
624
|
+
|
|
625
|
+
SINGLE_PAGE_WITH_BOOKMARK : Convert the PDF file into a single HTML file with an outline for navigation at the beginning of the HTML page
|
|
626
|
+
|
|
627
|
+
MULTIPLE_PAGE : Convert the PDF file into multiple HTML files
|
|
628
|
+
|
|
629
|
+
MULTIPLE_PAGE_WITH_BOOKMARK : Convert the PDF file into multiple HTML files. Each HTML file corresponds to a PDF page, and users can navigate to the next HTML file via a link at the bottom of the HTML page
|
|
630
|
+
"""
|
|
631
|
+
MULTIPLE_PAGE: typing.ClassVar[HtmlOption] # value = <HtmlOption.MULTIPLE_PAGE: 2>
|
|
632
|
+
MULTIPLE_PAGE_WITH_BOOKMARK: typing.ClassVar[HtmlOption] # value = <HtmlOption.MULTIPLE_PAGE_WITH_BOOKMARK: 3>
|
|
633
|
+
SINGLE_PAGE: typing.ClassVar[HtmlOption] # value = <HtmlOption.SINGLE_PAGE: 0>
|
|
634
|
+
SINGLE_PAGE_WITH_BOOKMARK: typing.ClassVar[HtmlOption] # value = <HtmlOption.SINGLE_PAGE_WITH_BOOKMARK: 1>
|
|
635
|
+
__members__: typing.ClassVar[dict[str, HtmlOption]] # value = {'SINGLE_PAGE': <HtmlOption.SINGLE_PAGE: 0>, 'SINGLE_PAGE_WITH_BOOKMARK': <HtmlOption.SINGLE_PAGE_WITH_BOOKMARK: 1>, 'MULTIPLE_PAGE': <HtmlOption.MULTIPLE_PAGE: 2>, 'MULTIPLE_PAGE_WITH_BOOKMARK': <HtmlOption.MULTIPLE_PAGE_WITH_BOOKMARK: 3>}
|
|
636
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
637
|
+
...
|
|
638
|
+
def __getstate__(self) -> int:
|
|
639
|
+
...
|
|
640
|
+
def __hash__(self) -> int:
|
|
641
|
+
...
|
|
642
|
+
def __index__(self) -> int:
|
|
643
|
+
...
|
|
644
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
645
|
+
...
|
|
646
|
+
def __int__(self) -> int:
|
|
647
|
+
...
|
|
648
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
649
|
+
...
|
|
650
|
+
def __repr__(self) -> str:
|
|
651
|
+
...
|
|
652
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
653
|
+
...
|
|
654
|
+
def __str__(self) -> str:
|
|
655
|
+
...
|
|
656
|
+
@property
|
|
657
|
+
def name(self) -> str:
|
|
658
|
+
...
|
|
659
|
+
@property
|
|
660
|
+
def value(self) -> int:
|
|
661
|
+
...
|
|
662
|
+
class ImageColorMode:
|
|
663
|
+
"""
|
|
664
|
+
Members:
|
|
665
|
+
|
|
666
|
+
COLOR : Color mode
|
|
667
|
+
|
|
668
|
+
GRAY : Gray mode
|
|
669
|
+
|
|
670
|
+
BINARY : Binary mode
|
|
671
|
+
"""
|
|
672
|
+
BINARY: typing.ClassVar[ImageColorMode] # value = <ImageColorMode.BINARY: 2>
|
|
673
|
+
COLOR: typing.ClassVar[ImageColorMode] # value = <ImageColorMode.COLOR: 0>
|
|
674
|
+
GRAY: typing.ClassVar[ImageColorMode] # value = <ImageColorMode.GRAY: 1>
|
|
675
|
+
__members__: typing.ClassVar[dict[str, ImageColorMode]] # value = {'COLOR': <ImageColorMode.COLOR: 0>, 'GRAY': <ImageColorMode.GRAY: 1>, 'BINARY': <ImageColorMode.BINARY: 2>}
|
|
676
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
677
|
+
...
|
|
678
|
+
def __getstate__(self) -> int:
|
|
679
|
+
...
|
|
680
|
+
def __hash__(self) -> int:
|
|
681
|
+
...
|
|
682
|
+
def __index__(self) -> int:
|
|
683
|
+
...
|
|
684
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
685
|
+
...
|
|
686
|
+
def __int__(self) -> int:
|
|
687
|
+
...
|
|
688
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
689
|
+
...
|
|
690
|
+
def __repr__(self) -> str:
|
|
691
|
+
...
|
|
692
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
693
|
+
...
|
|
694
|
+
def __str__(self) -> str:
|
|
695
|
+
...
|
|
696
|
+
@property
|
|
697
|
+
def name(self) -> str:
|
|
698
|
+
...
|
|
699
|
+
@property
|
|
700
|
+
def value(self) -> int:
|
|
701
|
+
...
|
|
702
|
+
class ImageType:
|
|
703
|
+
"""
|
|
704
|
+
Members:
|
|
705
|
+
|
|
706
|
+
JPG : .jpg
|
|
707
|
+
|
|
708
|
+
JPEG : .jpeg
|
|
709
|
+
|
|
710
|
+
JPEG2000 : .jp2
|
|
711
|
+
|
|
712
|
+
PNG : .png
|
|
713
|
+
|
|
714
|
+
BMP : .bmp
|
|
715
|
+
|
|
716
|
+
TIFF : .tiff
|
|
717
|
+
|
|
718
|
+
TGA : .tga
|
|
719
|
+
|
|
720
|
+
GIF : .gif
|
|
721
|
+
|
|
722
|
+
WEBP : .webp
|
|
723
|
+
"""
|
|
724
|
+
BMP: typing.ClassVar[ImageType] # value = <ImageType.BMP: 4>
|
|
725
|
+
GIF: typing.ClassVar[ImageType] # value = <ImageType.GIF: 7>
|
|
726
|
+
JPEG: typing.ClassVar[ImageType] # value = <ImageType.JPEG: 1>
|
|
727
|
+
JPEG2000: typing.ClassVar[ImageType] # value = <ImageType.JPEG2000: 2>
|
|
728
|
+
JPG: typing.ClassVar[ImageType] # value = <ImageType.JPG: 0>
|
|
729
|
+
PNG: typing.ClassVar[ImageType] # value = <ImageType.PNG: 3>
|
|
730
|
+
TGA: typing.ClassVar[ImageType] # value = <ImageType.TGA: 6>
|
|
731
|
+
TIFF: typing.ClassVar[ImageType] # value = <ImageType.TIFF: 5>
|
|
732
|
+
WEBP: typing.ClassVar[ImageType] # value = <ImageType.WEBP: 8>
|
|
733
|
+
__members__: typing.ClassVar[dict[str, ImageType]] # value = {'JPG': <ImageType.JPG: 0>, 'JPEG': <ImageType.JPEG: 1>, 'JPEG2000': <ImageType.JPEG2000: 2>, 'PNG': <ImageType.PNG: 3>, 'BMP': <ImageType.BMP: 4>, 'TIFF': <ImageType.TIFF: 5>, 'TGA': <ImageType.TGA: 6>, 'GIF': <ImageType.GIF: 7>, 'WEBP': <ImageType.WEBP: 8>}
|
|
734
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
735
|
+
...
|
|
736
|
+
def __getstate__(self) -> int:
|
|
737
|
+
...
|
|
738
|
+
def __hash__(self) -> int:
|
|
739
|
+
...
|
|
740
|
+
def __index__(self) -> int:
|
|
741
|
+
...
|
|
742
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
743
|
+
...
|
|
744
|
+
def __int__(self) -> int:
|
|
745
|
+
...
|
|
746
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
747
|
+
...
|
|
748
|
+
def __repr__(self) -> str:
|
|
749
|
+
...
|
|
750
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
751
|
+
...
|
|
752
|
+
def __str__(self) -> str:
|
|
753
|
+
...
|
|
754
|
+
@property
|
|
755
|
+
def name(self) -> str:
|
|
756
|
+
...
|
|
757
|
+
@property
|
|
758
|
+
def value(self) -> int:
|
|
759
|
+
...
|
|
760
|
+
class LicenseType:
|
|
761
|
+
"""
|
|
762
|
+
Type of the currently verified license.
|
|
763
|
+
|
|
764
|
+
Members:
|
|
765
|
+
|
|
766
|
+
UNKNOWN : No verified license type
|
|
767
|
+
|
|
768
|
+
TRIAL : Trial license
|
|
769
|
+
|
|
770
|
+
FORMAL : Formal license
|
|
771
|
+
"""
|
|
772
|
+
UNKNOWN: typing.ClassVar[LicenseType]
|
|
773
|
+
TRIAL: typing.ClassVar[LicenseType]
|
|
774
|
+
FORMAL: typing.ClassVar[LicenseType]
|
|
775
|
+
__members__: typing.ClassVar[dict[str, LicenseType]]
|
|
776
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None: ...
|
|
777
|
+
def __eq__(self, other: typing.Any) -> bool: ...
|
|
778
|
+
def __hash__(self) -> int: ...
|
|
779
|
+
def __index__(self) -> int: ...
|
|
780
|
+
def __int__(self) -> int: ...
|
|
781
|
+
@property
|
|
782
|
+
def name(self) -> str: ...
|
|
783
|
+
@property
|
|
784
|
+
def value(self) -> int: ...
|
|
785
|
+
|
|
786
|
+
class LibraryManager:
|
|
787
|
+
"""
|
|
788
|
+
The `LibraryManager` class serves as a central hub for managing the lifecycle of an SDK library. It provides functionalities such as verifying licenses, initializing and releasing the library, setting up logging, retrieving version information, counting pages in documents, querying the remaining page quota, and loading and releasing the DocumentAI model.
|
|
789
|
+
"""
|
|
790
|
+
@staticmethod
|
|
791
|
+
def get_page_count(file_path: str, password: str) -> int:
|
|
792
|
+
"""
|
|
793
|
+
Returns the number of pages in a document.
|
|
794
|
+
"""
|
|
795
|
+
@staticmethod
|
|
796
|
+
def get_remaining_page_quota() -> int:
|
|
797
|
+
"""
|
|
798
|
+
Returns the remaining page quota. >= 0: actual remaining pages, -1: not initialized, -2: unlimited, -3: quota file corrupted.
|
|
799
|
+
"""
|
|
800
|
+
@staticmethod
|
|
801
|
+
def get_license_type() -> LicenseType:
|
|
802
|
+
"""
|
|
803
|
+
Returns the currently verified license type without consuming quota.
|
|
804
|
+
UNKNOWN before verification, after failed verification, or while releasing.
|
|
805
|
+
"""
|
|
806
|
+
@staticmethod
|
|
807
|
+
def get_version() -> str:
|
|
808
|
+
"""
|
|
809
|
+
Gets the version of the SDK library.
|
|
810
|
+
"""
|
|
811
|
+
@staticmethod
|
|
812
|
+
def initialize(resource_path: str) -> None:
|
|
813
|
+
"""
|
|
814
|
+
Initializes the SDK library with the given resource path
|
|
815
|
+
"""
|
|
816
|
+
@staticmethod
|
|
817
|
+
def license_verify(license: str, device_id: str, app_id: str) -> ErrorCode:
|
|
818
|
+
"""
|
|
819
|
+
Verifies the provided license key along with device ID and application ID.
|
|
820
|
+
"""
|
|
821
|
+
@staticmethod
|
|
822
|
+
def release() -> None:
|
|
823
|
+
"""
|
|
824
|
+
Releases all resources used by the library. Should be called when the SDK is no longer needed. Active conversions finish first and new work is refused while release is pending.
|
|
825
|
+
"""
|
|
826
|
+
@staticmethod
|
|
827
|
+
def release_document_ai_model() -> None:
|
|
828
|
+
"""
|
|
829
|
+
Releases the memory used by the AI model. Cleanup is deferred until active conversions return. Call set_document_ai_model again before using AI functions.
|
|
830
|
+
"""
|
|
831
|
+
@staticmethod
|
|
832
|
+
def set_document_ai_model(file_path: str, gpu_id: typing.SupportsInt | typing.SupportsIndex = -1) -> ErrorCode:
|
|
833
|
+
"""
|
|
834
|
+
Loads the Document AI components contained in the given model package and merges them with the components already loaded. gpu_id: Which GPU to use for the AI model, -1 means disable GPU.
|
|
835
|
+
"""
|
|
836
|
+
@staticmethod
|
|
837
|
+
def set_document_ai_model_count(layout_model_count: typing.SupportsInt | typing.SupportsIndex, table_model_count: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
838
|
+
"""
|
|
839
|
+
Sets the number of AI models for layout analysis and table recognition.
|
|
840
|
+
"""
|
|
841
|
+
@staticmethod
|
|
842
|
+
def set_logger(enable_info: bool, enable_warning: bool) -> None:
|
|
843
|
+
"""
|
|
844
|
+
Enables or disables logging for info and warning messages.
|
|
845
|
+
"""
|
|
846
|
+
class OCRLanguage:
|
|
847
|
+
"""
|
|
848
|
+
Members:
|
|
849
|
+
|
|
850
|
+
UNKNOWN : Unknown language
|
|
851
|
+
|
|
852
|
+
CHINESE : Chinese (Simplified)
|
|
853
|
+
|
|
854
|
+
CHINESE_TRA : Chinese (Traditional)
|
|
855
|
+
|
|
856
|
+
ENGLISH : English
|
|
857
|
+
|
|
858
|
+
KOREAN : Korean
|
|
859
|
+
|
|
860
|
+
JAPANESE : Japanese
|
|
861
|
+
|
|
862
|
+
LATIN : Latin
|
|
863
|
+
|
|
864
|
+
DEVANAGARI : Devanagari
|
|
865
|
+
|
|
866
|
+
CYRILLIC : Cyrillic
|
|
867
|
+
|
|
868
|
+
ARABIC : Arabic
|
|
869
|
+
|
|
870
|
+
TAMIL : Tamil
|
|
871
|
+
|
|
872
|
+
TELUGU : Telugu
|
|
873
|
+
|
|
874
|
+
KANNADA : Kannada
|
|
875
|
+
|
|
876
|
+
THAI : Thai
|
|
877
|
+
|
|
878
|
+
GREEK : Greek
|
|
879
|
+
|
|
880
|
+
ESLAV : Eslav
|
|
881
|
+
|
|
882
|
+
AUTO : Automatically select language
|
|
883
|
+
"""
|
|
884
|
+
ARABIC: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.ARABIC: 9>
|
|
885
|
+
AUTO: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.AUTO: 16>
|
|
886
|
+
CHINESE: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.CHINESE: 1>
|
|
887
|
+
CHINESE_TRA: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.CHINESE_TRA: 2>
|
|
888
|
+
CYRILLIC: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.CYRILLIC: 8>
|
|
889
|
+
DEVANAGARI: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.DEVANAGARI: 7>
|
|
890
|
+
ENGLISH: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.ENGLISH: 3>
|
|
891
|
+
ESLAV: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.ESLAV: 15>
|
|
892
|
+
GREEK: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.GREEK: 14>
|
|
893
|
+
JAPANESE: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.JAPANESE: 5>
|
|
894
|
+
KANNADA: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.KANNADA: 12>
|
|
895
|
+
KOREAN: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.KOREAN: 4>
|
|
896
|
+
LATIN: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.LATIN: 6>
|
|
897
|
+
TAMIL: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.TAMIL: 10>
|
|
898
|
+
TELUGU: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.TELUGU: 11>
|
|
899
|
+
THAI: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.THAI: 13>
|
|
900
|
+
UNKNOWN: typing.ClassVar[OCRLanguage] # value = <OCRLanguage.UNKNOWN: 0>
|
|
901
|
+
__members__: typing.ClassVar[dict[str, OCRLanguage]] # value = {'UNKNOWN': <OCRLanguage.UNKNOWN: 0>, 'CHINESE': <OCRLanguage.CHINESE: 1>, 'CHINESE_TRA': <OCRLanguage.CHINESE_TRA: 2>, 'ENGLISH': <OCRLanguage.ENGLISH: 3>, 'KOREAN': <OCRLanguage.KOREAN: 4>, 'JAPANESE': <OCRLanguage.JAPANESE: 5>, 'LATIN': <OCRLanguage.LATIN: 6>, 'DEVANAGARI': <OCRLanguage.DEVANAGARI: 7>, 'CYRILLIC': <OCRLanguage.CYRILLIC: 8>, 'ARABIC': <OCRLanguage.ARABIC: 9>, 'TAMIL': <OCRLanguage.TAMIL: 10>, 'TELUGU': <OCRLanguage.TELUGU: 11>, 'KANNADA': <OCRLanguage.KANNADA: 12>, 'THAI': <OCRLanguage.THAI: 13>, 'GREEK': <OCRLanguage.GREEK: 14>, 'ESLAV': <OCRLanguage.ESLAV: 15>, 'AUTO': <OCRLanguage.AUTO: 16>}
|
|
902
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
903
|
+
...
|
|
904
|
+
def __getstate__(self) -> int:
|
|
905
|
+
...
|
|
906
|
+
def __hash__(self) -> int:
|
|
907
|
+
...
|
|
908
|
+
def __index__(self) -> int:
|
|
909
|
+
...
|
|
910
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
911
|
+
...
|
|
912
|
+
def __int__(self) -> int:
|
|
913
|
+
...
|
|
914
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
915
|
+
...
|
|
916
|
+
def __repr__(self) -> str:
|
|
917
|
+
...
|
|
918
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
919
|
+
...
|
|
920
|
+
def __str__(self) -> str:
|
|
921
|
+
...
|
|
922
|
+
@property
|
|
923
|
+
def name(self) -> str:
|
|
924
|
+
...
|
|
925
|
+
@property
|
|
926
|
+
def value(self) -> int:
|
|
927
|
+
...
|
|
928
|
+
class OCROption:
|
|
929
|
+
"""
|
|
930
|
+
Members:
|
|
931
|
+
|
|
932
|
+
INVALID_CHARACTER : Recognize illegal characters in PDF documents
|
|
933
|
+
|
|
934
|
+
SCAN_PAGE : Recognize scanned pages in PDF documents
|
|
935
|
+
|
|
936
|
+
INVALID_CHARACTER_AND_SCAN_PAGE : Recognize illegal characters and scanned pages in PDF documents
|
|
937
|
+
|
|
938
|
+
ALL : Recognize all characters on all pages
|
|
939
|
+
"""
|
|
940
|
+
ALL: typing.ClassVar[OCROption] # value = <OCROption.ALL: 3>
|
|
941
|
+
INVALID_CHARACTER: typing.ClassVar[OCROption] # value = <OCROption.INVALID_CHARACTER: 0>
|
|
942
|
+
INVALID_CHARACTER_AND_SCAN_PAGE: typing.ClassVar[OCROption] # value = <OCROption.INVALID_CHARACTER_AND_SCAN_PAGE: 2>
|
|
943
|
+
SCAN_PAGE: typing.ClassVar[OCROption] # value = <OCROption.SCAN_PAGE: 1>
|
|
944
|
+
__members__: typing.ClassVar[dict[str, OCROption]] # value = {'INVALID_CHARACTER': <OCROption.INVALID_CHARACTER: 0>, 'SCAN_PAGE': <OCROption.SCAN_PAGE: 1>, 'INVALID_CHARACTER_AND_SCAN_PAGE': <OCROption.INVALID_CHARACTER_AND_SCAN_PAGE: 2>, 'ALL': <OCROption.ALL: 3>}
|
|
945
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
946
|
+
...
|
|
947
|
+
def __getstate__(self) -> int:
|
|
948
|
+
...
|
|
949
|
+
def __hash__(self) -> int:
|
|
950
|
+
...
|
|
951
|
+
def __index__(self) -> int:
|
|
952
|
+
...
|
|
953
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
954
|
+
...
|
|
955
|
+
def __int__(self) -> int:
|
|
956
|
+
...
|
|
957
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
958
|
+
...
|
|
959
|
+
def __repr__(self) -> str:
|
|
960
|
+
...
|
|
961
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
962
|
+
...
|
|
963
|
+
def __str__(self) -> str:
|
|
964
|
+
...
|
|
965
|
+
@property
|
|
966
|
+
def name(self) -> str:
|
|
967
|
+
...
|
|
968
|
+
@property
|
|
969
|
+
def value(self) -> int:
|
|
970
|
+
...
|
|
971
|
+
class WordPdfBookmarkMode:
|
|
972
|
+
"""
|
|
973
|
+
How the PDF bookmarks (the outline shown in a reader's navigation panel) are generated when converting a Word document to PDF
|
|
974
|
+
|
|
975
|
+
Members:
|
|
976
|
+
|
|
977
|
+
NONE : Do not generate bookmarks
|
|
978
|
+
|
|
979
|
+
HEADINGS : One bookmark per heading (a paragraph with an outline level), nested by level
|
|
980
|
+
|
|
981
|
+
WORD_BOOKMARKS : One bookmark per Word bookmark, named after it
|
|
982
|
+
"""
|
|
983
|
+
HEADINGS: typing.ClassVar[WordPdfBookmarkMode] # value = <WordPdfBookmarkMode.HEADINGS: 1>
|
|
984
|
+
NONE: typing.ClassVar[WordPdfBookmarkMode] # value = <WordPdfBookmarkMode.NONE: 0>
|
|
985
|
+
WORD_BOOKMARKS: typing.ClassVar[WordPdfBookmarkMode] # value = <WordPdfBookmarkMode.WORD_BOOKMARKS: 2>
|
|
986
|
+
__members__: typing.ClassVar[dict[str, WordPdfBookmarkMode]] # value = {'NONE': <WordPdfBookmarkMode.NONE: 0>, 'HEADINGS': <WordPdfBookmarkMode.HEADINGS: 1>, 'WORD_BOOKMARKS': <WordPdfBookmarkMode.WORD_BOOKMARKS: 2>}
|
|
987
|
+
def __eq__(self, other: typing.Any) -> bool: ...
|
|
988
|
+
def __getstate__(self) -> int: ...
|
|
989
|
+
def __hash__(self) -> int: ...
|
|
990
|
+
def __index__(self) -> int: ...
|
|
991
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None: ...
|
|
992
|
+
def __int__(self) -> int: ...
|
|
993
|
+
def __ne__(self, other: typing.Any) -> bool: ...
|
|
994
|
+
def __repr__(self) -> str: ...
|
|
995
|
+
def __setstate__(self, state: int) -> None: ...
|
|
996
|
+
def __str__(self) -> str: ...
|
|
997
|
+
@property
|
|
998
|
+
def name(self) -> str: ...
|
|
999
|
+
@property
|
|
1000
|
+
def value(self) -> int: ...
|
|
1001
|
+
class PageLayoutMode:
|
|
1002
|
+
"""
|
|
1003
|
+
Members:
|
|
1004
|
+
|
|
1005
|
+
BOX : Box mode
|
|
1006
|
+
|
|
1007
|
+
FLOW : Flowing mode
|
|
1008
|
+
"""
|
|
1009
|
+
BOX: typing.ClassVar[PageLayoutMode] # value = <PageLayoutMode.BOX: 0>
|
|
1010
|
+
FLOW: typing.ClassVar[PageLayoutMode] # value = <PageLayoutMode.FLOW: 1>
|
|
1011
|
+
__members__: typing.ClassVar[dict[str, PageLayoutMode]] # value = {'BOX': <PageLayoutMode.BOX: 0>, 'FLOW': <PageLayoutMode.FLOW: 1>}
|
|
1012
|
+
def __eq__(self, other: typing.Any) -> bool:
|
|
1013
|
+
...
|
|
1014
|
+
def __getstate__(self) -> int:
|
|
1015
|
+
...
|
|
1016
|
+
def __hash__(self) -> int:
|
|
1017
|
+
...
|
|
1018
|
+
def __index__(self) -> int:
|
|
1019
|
+
...
|
|
1020
|
+
def __init__(self, value: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
1021
|
+
...
|
|
1022
|
+
def __int__(self) -> int:
|
|
1023
|
+
...
|
|
1024
|
+
def __ne__(self, other: typing.Any) -> bool:
|
|
1025
|
+
...
|
|
1026
|
+
def __repr__(self) -> str:
|
|
1027
|
+
...
|
|
1028
|
+
def __setstate__(self, state: typing.SupportsInt | typing.SupportsIndex) -> None:
|
|
1029
|
+
...
|
|
1030
|
+
def __str__(self) -> str:
|
|
1031
|
+
...
|
|
1032
|
+
@property
|
|
1033
|
+
def name(self) -> str:
|
|
1034
|
+
...
|
|
1035
|
+
@property
|
|
1036
|
+
def value(self) -> int:
|
|
1037
|
+
...
|
|
1038
|
+
ALL: OCROption # value = <OCROption.ALL: 3>
|
|
1039
|
+
ARABIC: OCRLanguage # value = <OCRLanguage.ARABIC: 9>
|
|
1040
|
+
AUTO: OCRLanguage # value = <OCRLanguage.AUTO: 16>
|
|
1041
|
+
BINARY: ImageColorMode # value = <ImageColorMode.BINARY: 2>
|
|
1042
|
+
BMP: ImageType # value = <ImageType.BMP: 4>
|
|
1043
|
+
BOX: PageLayoutMode # value = <PageLayoutMode.BOX: 0>
|
|
1044
|
+
CANCEL: ErrorCode # value = <ErrorCode.CANCEL: 1>
|
|
1045
|
+
CHINESE: OCRLanguage # value = <OCRLanguage.CHINESE: 1>
|
|
1046
|
+
CHINESE_TRA: OCRLanguage # value = <OCRLanguage.CHINESE_TRA: 2>
|
|
1047
|
+
COLOR: ImageColorMode # value = <ImageColorMode.COLOR: 0>
|
|
1048
|
+
COMPRESS_ERROR: ErrorCode # value = <ErrorCode.COMPRESS_ERROR: 9>
|
|
1049
|
+
CONVERTING_ERROR: ErrorCode # value = <ErrorCode.CONVERTING_ERROR: 60>
|
|
1050
|
+
CYRILLIC: OCRLanguage # value = <OCRLanguage.CYRILLIC: 8>
|
|
1051
|
+
DEVANAGARI: OCRLanguage # value = <OCRLanguage.DEVANAGARI: 7>
|
|
1052
|
+
ENGLISH: OCRLanguage # value = <OCRLanguage.ENGLISH: 3>
|
|
1053
|
+
ESLAV: OCRLanguage # value = <OCRLanguage.ESLAV: 15>
|
|
1054
|
+
EXPIRE_ERROR: ErrorCode # value = <ErrorCode.EXPIRE_ERROR: 90>
|
|
1055
|
+
FILE_ERROR: ErrorCode # value = <ErrorCode.FILE_ERROR: 2>
|
|
1056
|
+
FLOW: PageLayoutMode # value = <PageLayoutMode.FLOW: 1>
|
|
1057
|
+
FOR_DOCUMENT: ExcelWorksheetOption # value = <ExcelWorksheetOption.FOR_DOCUMENT: 2>
|
|
1058
|
+
FOR_PAGE: ExcelWorksheetOption # value = <ExcelWorksheetOption.FOR_PAGE: 1>
|
|
1059
|
+
FOR_TABLE: ExcelWorksheetOption # value = <ExcelWorksheetOption.FOR_TABLE: 0>
|
|
1060
|
+
GIF: ImageType # value = <ImageType.GIF: 7>
|
|
1061
|
+
GRAY: ImageColorMode # value = <ImageColorMode.GRAY: 1>
|
|
1062
|
+
GREEK: OCRLanguage # value = <OCRLanguage.GREEK: 14>
|
|
1063
|
+
IMAGE_DATA_EMPTY: ErrorCode # value = <ErrorCode.IMAGE_DATA_EMPTY: 86>
|
|
1064
|
+
IMAGE_FORMAT_UNSUPPORTED: ErrorCode # value = <ErrorCode.IMAGE_FORMAT_UNSUPPORTED: 88>
|
|
1065
|
+
IMAGE_INVALID: ErrorCode # value = <ErrorCode.IMAGE_INVALID: 89>
|
|
1066
|
+
IMAGE_WIDTH_HEIGHT_ERROR: ErrorCode # value = <ErrorCode.IMAGE_WIDTH_HEIGHT_ERROR: 87>
|
|
1067
|
+
INVALID_ARG: ErrorCode # value = <ErrorCode.INVALID_ARG: 80>
|
|
1068
|
+
INVALID_CHARACTER: OCROption # value = <OCROption.INVALID_CHARACTER: 0>
|
|
1069
|
+
INVALID_CHARACTER_AND_SCAN_PAGE: OCROption # value = <OCROption.INVALID_CHARACTER_AND_SCAN_PAGE: 2>
|
|
1070
|
+
INVALID_HANDLE: ErrorCode # value = <ErrorCode.INVALID_HANDLE: 81>
|
|
1071
|
+
INVALID_MODEL_FORMAT: ErrorCode # value = <ErrorCode.INVALID_MODEL_FORMAT: 82>
|
|
1072
|
+
INVALID_TABLE: ErrorCode # value = <ErrorCode.INVALID_TABLE: 94>
|
|
1073
|
+
IO_ERROR: ErrorCode # value = <ErrorCode.IO_ERROR: 8>
|
|
1074
|
+
JAPANESE: OCRLanguage # value = <OCRLanguage.JAPANESE: 5>
|
|
1075
|
+
JPEG: ImageType # value = <ImageType.JPEG: 1>
|
|
1076
|
+
JPEG2000: ImageType # value = <ImageType.JPEG2000: 2>
|
|
1077
|
+
JPG: ImageType # value = <ImageType.JPG: 0>
|
|
1078
|
+
KANNADA: OCRLanguage # value = <OCRLanguage.KANNADA: 12>
|
|
1079
|
+
KOREAN: OCRLanguage # value = <OCRLanguage.KOREAN: 4>
|
|
1080
|
+
LATIN: OCRLanguage # value = <OCRLanguage.LATIN: 6>
|
|
1081
|
+
LICENSE_CONCURRENCY_EXCEEDED: ErrorCode # value = <ErrorCode.LICENSE_CONCURRENCY_EXCEEDED: 30>
|
|
1082
|
+
LICENSE_EXPIRE: ErrorCode # value = <ErrorCode.LICENSE_EXPIRE: 21>
|
|
1083
|
+
LICENSE_FILE_READ_FAILED: ErrorCode # value = <ErrorCode.LICENSE_FILE_READ_FAILED: 28>
|
|
1084
|
+
LICENSE_ILLEGAL_ACCESS: ErrorCode # value = <ErrorCode.LICENSE_ILLEGAL_ACCESS: 27>
|
|
1085
|
+
LICENSE_INVALID: ErrorCode # value = <ErrorCode.LICENSE_INVALID: 20>
|
|
1086
|
+
LICENSE_MISMATCH: ErrorCode # value = <ErrorCode.LICENSE_MISMATCH: 93>
|
|
1087
|
+
LICENSE_OCR_PERMISSION_DENY: ErrorCode # value = <ErrorCode.LICENSE_OCR_PERMISSION_DENY: 29>
|
|
1088
|
+
LICENSE_PAGE_LIMIT_EXCEEDED: ErrorCode # value = <ErrorCode.LICENSE_PAGE_LIMIT_EXCEEDED: 31>
|
|
1089
|
+
LICENSE_PERMISSION_DENY: ErrorCode # value = <ErrorCode.LICENSE_PERMISSION_DENY: 25>
|
|
1090
|
+
LICENSE_QUOTA_CORRUPTED: ErrorCode # value = <ErrorCode.LICENSE_QUOTA_CORRUPTED: 32>
|
|
1091
|
+
LICENSE_UNINITIALIZED: ErrorCode # value = <ErrorCode.LICENSE_UNINITIALIZED: 26>
|
|
1092
|
+
LICENSE_UNSUPPORTED_API: ErrorCode # value = <ErrorCode.LICENSE_UNSUPPORTED_API: 92>
|
|
1093
|
+
LICENSE_UNSUPPORTED_DEVICE: ErrorCode # value = <ErrorCode.LICENSE_UNSUPPORTED_DEVICE: 24>
|
|
1094
|
+
LICENSE_UNSUPPORTED_ID: ErrorCode # value = <ErrorCode.LICENSE_UNSUPPORTED_ID: 23>
|
|
1095
|
+
LICENSE_UNSUPPORTED_PLATFORM: ErrorCode # value = <ErrorCode.LICENSE_UNSUPPORTED_PLATFORM: 22>
|
|
1096
|
+
MISSING_ARG: ErrorCode # value = <ErrorCode.MISSING_ARG: 91>
|
|
1097
|
+
MODEL_FORMAT_UNSUPPORTED: ErrorCode # value = <ErrorCode.MODEL_FORMAT_UNSUPPORTED: 84>
|
|
1098
|
+
MODEL_FUNCTION_UNSUPPORTED: ErrorCode # value = <ErrorCode.MODEL_FUNCTION_UNSUPPORTED: 83>
|
|
1099
|
+
MODEL_SDK_MISMATCH: ErrorCode # value = <ErrorCode.MODEL_SDK_MISMATCH: 85>
|
|
1100
|
+
MULTIPLE_PAGE: HtmlOption # value = <HtmlOption.MULTIPLE_PAGE: 2>
|
|
1101
|
+
MULTIPLE_PAGE_WITH_BOOKMARK: HtmlOption # value = <HtmlOption.MULTIPLE_PAGE_WITH_BOOKMARK: 3>
|
|
1102
|
+
NO_TABLE_ERROR: ErrorCode # value = <ErrorCode.NO_TABLE_ERROR: 40>
|
|
1103
|
+
OCR_FAILURE: ErrorCode # value = <ErrorCode.OCR_FAILURE: 41>
|
|
1104
|
+
OUT_OF_MEMORY: ErrorCode # value = <ErrorCode.OUT_OF_MEMORY: 7>
|
|
1105
|
+
PDF_FORMAT_ERROR: ErrorCode # value = <ErrorCode.PDF_FORMAT_ERROR: 5>
|
|
1106
|
+
PDF_PAGE_ERROR: ErrorCode # value = <ErrorCode.PDF_PAGE_ERROR: 4>
|
|
1107
|
+
PDF_PASSWORD_ERROR: ErrorCode # value = <ErrorCode.PDF_PASSWORD_ERROR: 3>
|
|
1108
|
+
PDF_SECURITY_ERROR: ErrorCode # value = <ErrorCode.PDF_SECURITY_ERROR: 6>
|
|
1109
|
+
PNG: ImageType # value = <ImageType.PNG: 3>
|
|
1110
|
+
SCAN_PAGE: OCROption # value = <OCROption.SCAN_PAGE: 1>
|
|
1111
|
+
SINGLE_PAGE: HtmlOption # value = <HtmlOption.SINGLE_PAGE: 0>
|
|
1112
|
+
SINGLE_PAGE_WITH_BOOKMARK: HtmlOption # value = <HtmlOption.SINGLE_PAGE_WITH_BOOKMARK: 1>
|
|
1113
|
+
SUCCESS: ErrorCode # value = <ErrorCode.SUCCESS: 0>
|
|
1114
|
+
TAMIL: OCRLanguage # value = <OCRLanguage.TAMIL: 10>
|
|
1115
|
+
TELUGU: OCRLanguage # value = <OCRLanguage.TELUGU: 11>
|
|
1116
|
+
TGA: ImageType # value = <ImageType.TGA: 6>
|
|
1117
|
+
THAI: OCRLanguage # value = <OCRLanguage.THAI: 13>
|
|
1118
|
+
TIFF: ImageType # value = <ImageType.TIFF: 5>
|
|
1119
|
+
UNKNOWN: OCRLanguage # value = <OCRLanguage.UNKNOWN: 0>
|
|
1120
|
+
UNKNOWN_ERROR: ErrorCode # value = <ErrorCode.UNKNOWN_ERROR: 100>
|
|
1121
|
+
UNSUPPORTED_FEATURE: ErrorCode # value = <ErrorCode.UNSUPPORTED_FEATURE: 95>
|
|
1122
|
+
WEBP: ImageType # value = <ImageType.WEBP: 8>
|
|
1123
|
+
HEADINGS: WordPdfBookmarkMode
|
|
1124
|
+
NONE: WordPdfBookmarkMode
|
|
1125
|
+
WORD_BOOKMARKS: WordPdfBookmarkMode
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
File without changes
|
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: ComPDFKitConversion
|
|
3
|
+
Version: 4.3.0
|
|
4
|
+
Summary: Conversion Python SDK
|
|
5
|
+
Home-page:
|
|
6
|
+
Author:
|
|
7
|
+
Author-email:
|
|
8
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
9
|
+
Classifier: Operating System :: MacOS
|
|
10
|
+
Classifier: Intended Audience :: Developers
|
|
11
|
+
Requires-Python: >=3.8
|
|
12
|
+
Description-Content-Type: text/markdown
|
|
13
|
+
Dynamic: classifier
|
|
14
|
+
Dynamic: description
|
|
15
|
+
Dynamic: description-content-type
|
|
16
|
+
Dynamic: requires-python
|
|
17
|
+
Dynamic: summary
|
|
18
|
+
|
|
19
|
+
# Conversion SDK For Python
|
|
20
|
+
|
|
21
|
+
Conversion SDK is a high-performance library designed for extracting and transforming the data within your PDF files, such as text, images, tables, links, and annotations, into various file formats. Our Conversion SDK retains the original document layout and the properties of the file data, ensuring a seamless document conversion experience.
|
|
22
|
+
|
|
23
|
+
Effortlessly integrate the Conversion SDK into your projects in just a few steps, and enable the following file format conversions:
|
|
24
|
+
|
|
25
|
+
- Convert PDF to Word (.docx)
|
|
26
|
+
- Convert PDF to Excel (.xlsx)
|
|
27
|
+
- Convert PDF to PowerPoint (.pptx)
|
|
28
|
+
- Convert PDF to HTML (.html)
|
|
29
|
+
- Convert PDF to CSV (.csv)
|
|
30
|
+
- Convert PDF to Image (.png, .jpg, .jpeg, .bmp, .tiff)
|
|
31
|
+
- Convert PDF to Plain Text (.txt)
|
|
32
|
+
- Convert PDF to Rich Text Format (.rtf)
|
|
33
|
+
- Convert PDF to Structured Data (.json)
|
|
34
|
+
- Convert PDF to Markdown (.md)
|
|
35
|
+
|
|
36
|
+
Harness the power of Conversion SDK and take your document processing to the next level with intelligent tools designed for accuracy and efficiency. To enhance your format conversion results, Conversion SDK offers AI-powered document tools with the following capabilities:
|
|
37
|
+
|
|
38
|
+
- Optical Character Recognition (OCR)
|
|
39
|
+
- Layout Analysis
|
|
40
|
+
- Table Recognition
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
## Why Conversion SDK
|
|
44
|
+
|
|
45
|
+
- Mature Technology
|
|
46
|
+
|
|
47
|
+
With years of technology accumulation, we have established a complete mechanism of product iteration to offer a continuous guarantee for product competitiveness.
|
|
48
|
+
|
|
49
|
+
- Complete PDF and Format Conversion Functionalities
|
|
50
|
+
|
|
51
|
+
Our comprehensive features can meet diverse needs and are easy for our customers to use without training costs.
|
|
52
|
+
|
|
53
|
+
- High-quality Service
|
|
54
|
+
|
|
55
|
+
professional service and technical support to quickly respond to users' feedback through onsite service or remote support like telephone, email, etc.
|
|
56
|
+
|
|
57
|
+
- Independent Intellectual
|
|
58
|
+
|
|
59
|
+
Property Rights
|
|
60
|
+
Our technology is independent and compliant with ISO, helping enterprises conduct international business without considering copyright risks.
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
## Conversion SDK
|
|
64
|
+
|
|
65
|
+
The Conversion SDK is designed to facilitate the effortless conversion of PDF files into various other formats, all while preserving the original layout and formatting of the documents. In this guide, we will explore the Conversion SDK and demonstrate how to utilize it within your Windows projects.
|
|
66
|
+
|
|
67
|
+
## License & Trial
|
|
68
|
+
|
|
69
|
+
The Conversion SDK is a commercial SDK that requires a license to grant developers the right to develop and distribute their applications. In development mode, each license is only valid for one device ID. However, even if you have a license, it is prohibited to distribute any documents, sample code, or source code of the Conversion SDK to any third parties.
|
|
70
|
+
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
ComPDFKitConversion/_core.cpython-313-darwin.so,sha256=RAIidL8zQVkyMVx5fPFIY3-nhdyaYfbnzfq5E3VuwXo,1369664
|
|
2
|
+
ComPDFKitConversion/__init__.pyi,sha256=sIuumOJvfvvTfAucBuNIIwkqBXNitmVLBsft4XueI8c,617
|
|
3
|
+
ComPDFKitConversion/_core.pyi,sha256=_J1qT1G4eU1t6U4TrAzG8LSwDzbGIghrIQ6qktfEKto,50875
|
|
4
|
+
ComPDFKitConversion/libopencv_world.410.dylib,sha256=GKCJ3TaDvKzaGuoJg--DIynAN-LelWr4Q7yIMwI7lls,15755152
|
|
5
|
+
ComPDFKitConversion/__init__.py,sha256=OcgoqodZa-29ZcR7lhSyQUjL6ST3vdYr_JX-MbPBxnM,905
|
|
6
|
+
ComPDFKitConversion/libonnxruntime.1.18.0.dylib,sha256=4LB_vOvww04ZyeTs-gsICNfPObiq86h-daiAIi8bRlc,24726224
|
|
7
|
+
ComPDFKitConversion/libcpdfconversionsdk.dylib,sha256=NuuMYL-e6xhKqmOBSw0WFQvE1SkIlNoC1ZlI44oi2mo,40638640
|
|
8
|
+
ComPDFKitConversion/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
9
|
+
ComPDFKitConversion/libDocumentAI.4.3.0.dylib,sha256=MBp56Cvi9hSoI4yKWptrP5oBgzPQoTAvLCQaHVEOqKQ,5064592
|
|
10
|
+
ComPDFKitConversion/.dylibs/libc++.1.0.dylib,sha256=lt6ktkwC754jy3Is2-v5NvOORDmHoNZEsWFOFQDss3s,1185696
|
|
11
|
+
compdfkitconversion-4.3.0.dist-info/RECORD,,
|
|
12
|
+
compdfkitconversion-4.3.0.dist-info/WHEEL,sha256=W9vNsxHtuPjBar6tWy08iHBg_jNK-VgyOpoyoNPwHv0,136
|
|
13
|
+
compdfkitconversion-4.3.0.dist-info/top_level.txt,sha256=wiM_kGlJ-WTJMAUWmnkl4wlQx6IyHEBDUkyHSo_IfWc,20
|
|
14
|
+
compdfkitconversion-4.3.0.dist-info/METADATA,sha256=Rswret-p_E3lQ1ivu-2s_WNRKLxGwVOuz5I1ALM2qhQ,3113
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
ComPDFKitConversion
|