diff --git a/README.md b/README.md index a98a7ae..3dd0a77 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ The powerful Optical Character Recognition (OCR) APIs let you convert scanned im This Python package provides a native API client for [Cloudmersive OCR](https://www.cloudmersive.com/ocr-api) - API version: v1 -- Package version: 2.1.9 +- Package version: 2.2.0 - Build package: io.swagger.codegen.languages.PythonClientCodegen ## Requirements. diff --git a/cloudmersive_ocr_api_client/api/image_ocr_api.py b/cloudmersive_ocr_api_client/api/image_ocr_api.py index e6499d7..557f37a 100644 --- a/cloudmersive_ocr_api_client/api/image_ocr_api.py +++ b/cloudmersive_ocr_api_client/api/image_ocr_api.py @@ -706,7 +706,7 @@ def image_ocr_photo_to_text(self, image_file, **kwargs): # noqa: E501 :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :return: ImageToTextResponse If the method is called asynchronously, @@ -730,7 +730,7 @@ def image_ocr_photo_to_text_with_http_info(self, image_file, **kwargs): # noqa: :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :return: ImageToTextResponse If the method is called asynchronously, @@ -813,7 +813,7 @@ def image_ocr_photo_words_with_location(self, image_file, **kwargs): # noqa: E5 :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :param str diagnostics: Optional, diagnostics mode, default is 'false'. Possible values are 'true' (will set DiagnosticImage to a diagnostic PNG image in the result), and 'false' (no diagnostics are enabled; this is recommended for best performance). @@ -839,7 +839,7 @@ def image_ocr_photo_words_with_location_with_http_info(self, image_file, **kwarg :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :param str diagnostics: Optional, diagnostics mode, default is 'false'. Possible values are 'true' (will set DiagnosticImage to a diagnostic PNG image in the result), and 'false' (no diagnostics are enabled; this is recommended for best performance). @@ -928,7 +928,7 @@ def image_ocr_post(self, image_file, **kwargs): # noqa: E501 :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :return: ImageToTextResponse @@ -953,7 +953,7 @@ def image_ocr_post_with_http_info(self, image_file, **kwargs): # noqa: E501 :param async_req bool :param file image_file: Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. (required) - :param str recognition_mode: Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :return: ImageToTextResponse diff --git a/cloudmersive_ocr_api_client/api/pdf_ocr_api.py b/cloudmersive_ocr_api_client/api/pdf_ocr_api.py index 96bf319..babe658 100644 --- a/cloudmersive_ocr_api_client/api/pdf_ocr_api.py +++ b/cloudmersive_ocr_api_client/api/pdf_ocr_api.py @@ -257,6 +257,7 @@ def pdf_ocr_post(self, image_file, **kwargs): # noqa: E501 :param async_req bool :param file image_file: PDF file to perform OCR on. (required) + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls per page; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls per page; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls per page. Default recognition mode is 'Basic' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :return: PdfToTextResponse @@ -280,6 +281,7 @@ def pdf_ocr_post_with_http_info(self, image_file, **kwargs): # noqa: E501 :param async_req bool :param file image_file: PDF file to perform OCR on. (required) + :param str recognition_mode: Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls per page; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls per page; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls per page. Default recognition mode is 'Basic' :param str language: Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) :param str preprocessing: Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). :return: PdfToTextResponse @@ -287,7 +289,7 @@ def pdf_ocr_post_with_http_info(self, image_file, **kwargs): # noqa: E501 returns the request thread. """ - all_params = ['image_file', 'language', 'preprocessing'] # noqa: E501 + all_params = ['image_file', 'recognition_mode', 'language', 'preprocessing'] # noqa: E501 all_params.append('async_req') all_params.append('_return_http_data_only') all_params.append('_preload_content') @@ -314,6 +316,8 @@ def pdf_ocr_post_with_http_info(self, image_file, **kwargs): # noqa: E501 query_params = [] header_params = {} + if 'recognition_mode' in params: + header_params['recognitionMode'] = params['recognition_mode'] # noqa: E501 if 'language' in params: header_params['language'] = params['language'] # noqa: E501 if 'preprocessing' in params: diff --git a/cloudmersive_ocr_api_client/api_client.py b/cloudmersive_ocr_api_client/api_client.py index 30e83e0..5006181 100644 --- a/cloudmersive_ocr_api_client/api_client.py +++ b/cloudmersive_ocr_api_client/api_client.py @@ -74,7 +74,7 @@ def __init__(self, configuration=None, header_name=None, header_value=None, self.default_headers[header_name] = header_value self.cookie = cookie # Set default User-Agent. - self.user_agent = 'Swagger-Codegen/2.1.9/python' + self.user_agent = 'Swagger-Codegen/2.2.0/python' def __del__(self): if self._pool is not None: diff --git a/cloudmersive_ocr_api_client/configuration.py b/cloudmersive_ocr_api_client/configuration.py index 53bbdc9..96d5255 100644 --- a/cloudmersive_ocr_api_client/configuration.py +++ b/cloudmersive_ocr_api_client/configuration.py @@ -240,5 +240,5 @@ def to_debug_report(self): "OS: {env}\n"\ "Python Version: {pyversion}\n"\ "Version of the API: v1\n"\ - "SDK Package Version: 2.1.9".\ + "SDK Package Version: 2.2.0".\ format(env=sys.platform, pyversion=sys.version) diff --git a/docs/ImageOcrApi.md b/docs/ImageOcrApi.md index b55bc2d..525d0ca 100644 --- a/docs/ImageOcrApi.md +++ b/docs/ImageOcrApi.md @@ -397,7 +397,7 @@ configuration.api_key['Apikey'] = 'YOUR_API_KEY' # create an instance of the API class api_instance = cloudmersive_ocr_api_client.ImageOcrApi(cloudmersive_ocr_api_client.ApiClient(configuration)) image_file = '/path/to/file.txt' # file | Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. -recognition_mode = 'recognition_mode_example' # str | Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' (optional) +recognition_mode = 'recognition_mode_example' # str | Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' (optional) language = 'language_example' # str | Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) (optional) try: @@ -413,7 +413,7 @@ except ApiException as e: Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **image_file** | **file**| Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. | - **recognition_mode** | **str**| Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' | [optional] + **recognition_mode** | **str**| Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' | [optional] **language** | **str**| Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) | [optional] ### Return type @@ -455,7 +455,7 @@ configuration.api_key['Apikey'] = 'YOUR_API_KEY' # create an instance of the API class api_instance = cloudmersive_ocr_api_client.ImageOcrApi(cloudmersive_ocr_api_client.ApiClient(configuration)) image_file = '/path/to/file.txt' # file | Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. -recognition_mode = 'recognition_mode_example' # str | Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' (optional) +recognition_mode = 'recognition_mode_example' # str | Optional; possible values are 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' (optional) language = 'language_example' # str | Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) (optional) preprocessing = 'preprocessing_example' # str | Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). (optional) diagnostics = 'diagnostics_example' # str | Optional, diagnostics mode, default is 'false'. Possible values are 'true' (will set DiagnosticImage to a diagnostic PNG image in the result), and 'false' (no diagnostics are enabled; this is recommended for best performance). (optional) @@ -473,7 +473,7 @@ except ApiException as e: Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **image_file** | **file**| Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. | - **recognition_mode** | **str**| Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' | [optional] + **recognition_mode** | **str**| Optional; possible values are 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' | [optional] **language** | **str**| Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) | [optional] **preprocessing** | **str**| Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). | [optional] **diagnostics** | **str**| Optional, diagnostics mode, default is 'false'. Possible values are 'true' (will set DiagnosticImage to a diagnostic PNG image in the result), and 'false' (no diagnostics are enabled; this is recommended for best performance). | [optional] @@ -517,7 +517,7 @@ configuration.api_key['Apikey'] = 'YOUR_API_KEY' # create an instance of the API class api_instance = cloudmersive_ocr_api_client.ImageOcrApi(cloudmersive_ocr_api_client.ApiClient(configuration)) image_file = '/path/to/file.txt' # file | Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. -recognition_mode = 'recognition_mode_example' # str | Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' (optional) +recognition_mode = 'recognition_mode_example' # str | Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' (optional) language = 'language_example' # str | Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) (optional) preprocessing = 'preprocessing_example' # str | Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). (optional) @@ -534,7 +534,7 @@ except ApiException as e: Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **image_file** | **file**| Image file to perform OCR on. Common file formats such as PNG, JPEG are supported. | - **recognition_mode** | **str**| Optional, default recognition mode is 'Advanced', enable default recognition mode by specifying 'Normal' | [optional] + **recognition_mode** | **str**| Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls. Default recognition mode is 'Advanced' | [optional] **language** | **str**| Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) | [optional] **preprocessing** | **str**| Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). | [optional] diff --git a/docs/PdfOcrApi.md b/docs/PdfOcrApi.md index adcd02a..c28f3be 100644 --- a/docs/PdfOcrApi.md +++ b/docs/PdfOcrApi.md @@ -126,7 +126,7 @@ Name | Type | Description | Notes [[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md) # **pdf_ocr_post** -> PdfToTextResponse pdf_ocr_post(image_file, language=language, preprocessing=preprocessing) +> PdfToTextResponse pdf_ocr_post(image_file, recognition_mode=recognition_mode, language=language, preprocessing=preprocessing) Converts an uploaded PDF file into text via Optical Character Recognition. @@ -147,12 +147,13 @@ configuration.api_key['Apikey'] = 'YOUR_API_KEY' # create an instance of the API class api_instance = cloudmersive_ocr_api_client.PdfOcrApi(cloudmersive_ocr_api_client.ApiClient(configuration)) image_file = '/path/to/file.txt' # file | PDF file to perform OCR on. +recognition_mode = 'recognition_mode_example' # str | Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls per page; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls per page; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls per page. Default recognition mode is 'Basic' (optional) language = 'language_example' # str | Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) (optional) preprocessing = 'preprocessing_example' # str | Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). (optional) try: # Converts an uploaded PDF file into text via Optical Character Recognition. - api_response = api_instance.pdf_ocr_post(image_file, language=language, preprocessing=preprocessing) + api_response = api_instance.pdf_ocr_post(image_file, recognition_mode=recognition_mode, language=language, preprocessing=preprocessing) pprint(api_response) except ApiException as e: print("Exception when calling PdfOcrApi->pdf_ocr_post: %s\n" % e) @@ -163,6 +164,7 @@ except ApiException as e: Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- **image_file** | **file**| PDF file to perform OCR on. | + **recognition_mode** | **str**| Optional; possible values are 'Basic' which provides basic recognition and is not resillient to page rotation, skew or low quality images uses 1-2 API calls per page; 'Normal' which provides highly fault tolerant OCR recognition uses 14-16 API calls per page; and 'Advanced' which provides the highest quality and most fault-tolerant recognition uses 28-30 API calls per page. Default recognition mode is 'Basic' | [optional] **language** | **str**| Optional, language of the input document, default is English (ENG). Possible values are ENG (English), ARA (Arabic), ZHO (Chinese - Simplified), ZHO-HANT (Chinese - Traditional), ASM (Assamese), AFR (Afrikaans), AMH (Amharic), AZE (Azerbaijani), AZE-CYRL (Azerbaijani - Cyrillic), BEL (Belarusian), BEN (Bengali), BOD (Tibetan), BOS (Bosnian), BUL (Bulgarian), CAT (Catalan; Valencian), CEB (Cebuano), CES (Czech), CHR (Cherokee), CYM (Welsh), DAN (Danish), DEU (German), DZO (Dzongkha), ELL (Greek), ENM (Archaic/Middle English), EPO (Esperanto), EST (Estonian), EUS (Basque), FAS (Persian), FIN (Finnish), FRA (French), FRK (Frankish), FRM (Middle-French), GLE (Irish), GLG (Galician), GRC (Ancient Greek), HAT (Hatian), HEB (Hebrew), HIN (Hindi), HRV (Croatian), HUN (Hungarian), IKU (Inuktitut), IND (Indonesian), ISL (Icelandic), ITA (Italian), ITA-OLD (Old - Italian), JAV (Javanese), JPN (Japanese), KAN (Kannada), KAT (Georgian), KAT-OLD (Old-Georgian), KAZ (Kazakh), KHM (Central Khmer), KIR (Kirghiz), KOR (Korean), KUR (Kurdish), LAO (Lao), LAT (Latin), LAV (Latvian), LIT (Lithuanian), MAL (Malayalam), MAR (Marathi), MKD (Macedonian), MLT (Maltese), MSA (Malay), MYA (Burmese), NEP (Nepali), NLD (Dutch), NOR (Norwegian), ORI (Oriya), PAN (Panjabi), POL (Polish), POR (Portuguese), PUS (Pushto), RON (Romanian), RUS (Russian), SAN (Sanskrit), SIN (Sinhala), SLK (Slovak), SLV (Slovenian), SPA (Spanish), SPA-OLD (Old Spanish), SQI (Albanian), SRP (Serbian), SRP-LAT (Latin Serbian), SWA (Swahili), SWE (Swedish), SYR (Syriac), TAM (Tamil), TEL (Telugu), TGK (Tajik), TGL (Tagalog), THA (Thai), TIR (Tigrinya), TUR (Turkish), UIG (Uighur), UKR (Ukrainian), URD (Urdu), UZB (Uzbek), UZB-CYR (Cyrillic Uzbek), VIE (Vietnamese), YID (Yiddish) | [optional] **preprocessing** | **str**| Optional, preprocessing mode, default is 'Auto'. Possible values are None (no preprocessing of the image), and Auto (automatic image enhancement of the image before OCR is applied; this is recommended). | [optional] diff --git a/packageconfig.json b/packageconfig.json index 018895d..0470e69 100644 --- a/packageconfig.json +++ b/packageconfig.json @@ -1,6 +1,6 @@ { "projectName" : "cloudmersive_ocr_api_client", "packageName" : "cloudmersive_ocr_api_client", - "packageVersion": "2.1.9", + "packageVersion": "2.2.0", "packageUrl": "https://www.cloudmersive.com/ocr-api" } \ No newline at end of file diff --git a/setup.py b/setup.py index 75b345c..ac707be 100644 --- a/setup.py +++ b/setup.py @@ -14,7 +14,7 @@ from setuptools import setup, find_packages # noqa: H301 NAME = "cloudmersive_ocr_api_client" -VERSION = "2.1.9" +VERSION = "2.2.0" # To install the library, run the following # # python setup.py install