cloudmersive-ocr-api-client 1.2.9
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/Gemfile +7 -0
- data/README.md +111 -0
- data/Rakefile +8 -0
- data/cloudmersive-ocr-api-client.gemspec +45 -0
- data/docs/ImageOcrApi.md +128 -0
- data/docs/ImageToTextResponse.md +9 -0
- data/docs/OcrPageResult.md +10 -0
- data/docs/PdfOcrApi.md +67 -0
- data/docs/PdfToTextResponse.md +9 -0
- data/docs/PreprocessingApi.md +118 -0
- data/git_push.sh +55 -0
- data/lib/cloudmersive-ocr-api-client.rb +45 -0
- data/lib/cloudmersive-ocr-api-client/api/image_ocr_api.rb +144 -0
- data/lib/cloudmersive-ocr-api-client/api/pdf_ocr_api.rb +85 -0
- data/lib/cloudmersive-ocr-api-client/api/preprocessing_api.rb +135 -0
- data/lib/cloudmersive-ocr-api-client/api_client.rb +389 -0
- data/lib/cloudmersive-ocr-api-client/api_error.rb +38 -0
- data/lib/cloudmersive-ocr-api-client/configuration.rb +209 -0
- data/lib/cloudmersive-ocr-api-client/models/image_to_text_response.rb +199 -0
- data/lib/cloudmersive-ocr-api-client/models/ocr_page_result.rb +209 -0
- data/lib/cloudmersive-ocr-api-client/models/pdf_to_text_response.rb +199 -0
- data/lib/cloudmersive-ocr-api-client/version.rb +15 -0
- data/spec/api/image_ocr_api_spec.rb +62 -0
- data/spec/api/pdf_ocr_api_spec.rb +49 -0
- data/spec/api/preprocessing_api_spec.rb +59 -0
- data/spec/api_client_spec.rb +226 -0
- data/spec/configuration_spec.rb +42 -0
- data/spec/models/image_to_text_response_spec.rb +48 -0
- data/spec/models/ocr_page_result_spec.rb +54 -0
- data/spec/models/pdf_to_text_response_spec.rb +48 -0
- data/spec/spec_helper.rb +111 -0
- metadata +255 -0
data/git_push.sh
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
#!/bin/sh
|
2
|
+
#
|
3
|
+
# Generated by: https://github.com/swagger-api/swagger-codegen.git
|
4
|
+
#
|
5
|
+
# ref: https://help.github.com/articles/adding-an-existing-project-to-github-using-the-command-line/
|
6
|
+
#
|
7
|
+
# Usage example: /bin/sh ./git_push.sh wing328 swagger-petstore-perl "minor update"
|
8
|
+
|
9
|
+
git_user_id=$1
|
10
|
+
git_repo_id=$2
|
11
|
+
release_note=$3
|
12
|
+
|
13
|
+
if [ "$git_user_id" = "" ]; then
|
14
|
+
git_user_id="GIT_USER_ID"
|
15
|
+
echo "[INFO] No command line input provided. Set \$git_user_id to $git_user_id"
|
16
|
+
fi
|
17
|
+
|
18
|
+
if [ "$git_repo_id" = "" ]; then
|
19
|
+
git_repo_id="GIT_REPO_ID"
|
20
|
+
echo "[INFO] No command line input provided. Set \$git_repo_id to $git_repo_id"
|
21
|
+
fi
|
22
|
+
|
23
|
+
if [ "$release_note" = "" ]; then
|
24
|
+
release_note="Minor update"
|
25
|
+
echo "[INFO] No command line input provided. Set \$release_note to $release_note"
|
26
|
+
fi
|
27
|
+
|
28
|
+
# Initialize the local directory as a Git repository
|
29
|
+
git init
|
30
|
+
|
31
|
+
# Adds the files in the local repository and stages them for commit.
|
32
|
+
git add .
|
33
|
+
|
34
|
+
# Commits the tracked changes and prepares them to be pushed to a remote repository.
|
35
|
+
git commit -m "$release_note"
|
36
|
+
|
37
|
+
# Sets the new remote
|
38
|
+
git_remote=`git remote`
|
39
|
+
if [ "$git_remote" = "" ]; then # git remote not defined
|
40
|
+
|
41
|
+
if [ "$GIT_TOKEN" = "" ]; then
|
42
|
+
echo "[INFO] \$GIT_TOKEN (environment variable) is not set. Using the git credential in your environment."
|
43
|
+
git remote add origin https://github.com/${git_user_id}/${git_repo_id}.git
|
44
|
+
else
|
45
|
+
git remote add origin https://${git_user_id}:${GIT_TOKEN}@github.com/${git_user_id}/${git_repo_id}.git
|
46
|
+
fi
|
47
|
+
|
48
|
+
fi
|
49
|
+
|
50
|
+
git pull origin master
|
51
|
+
|
52
|
+
# Pushes (Forces) the changes in the local repository up to the remote repository
|
53
|
+
echo "Git pushing to https://github.com/${git_user_id}/${git_repo_id}.git"
|
54
|
+
git push origin master 2>&1 | grep -v 'To https'
|
55
|
+
|
@@ -0,0 +1,45 @@
|
|
1
|
+
=begin
|
2
|
+
#ocrapi
|
3
|
+
|
4
|
+
#The powerful Optical Character Recognition (OCR) APIs let you convert scanned images of pages into recognized text.
|
5
|
+
|
6
|
+
OpenAPI spec version: v1
|
7
|
+
|
8
|
+
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
9
|
+
Swagger Codegen version: unset
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
# Common files
|
14
|
+
require 'cloudmersive-ocr-api-client/api_client'
|
15
|
+
require 'cloudmersive-ocr-api-client/api_error'
|
16
|
+
require 'cloudmersive-ocr-api-client/version'
|
17
|
+
require 'cloudmersive-ocr-api-client/configuration'
|
18
|
+
|
19
|
+
# Models
|
20
|
+
require 'cloudmersive-ocr-api-client/models/image_to_text_response'
|
21
|
+
require 'cloudmersive-ocr-api-client/models/ocr_page_result'
|
22
|
+
require 'cloudmersive-ocr-api-client/models/pdf_to_text_response'
|
23
|
+
|
24
|
+
# APIs
|
25
|
+
require 'cloudmersive-ocr-api-client/api/image_ocr_api'
|
26
|
+
require 'cloudmersive-ocr-api-client/api/pdf_ocr_api'
|
27
|
+
require 'cloudmersive-ocr-api-client/api/preprocessing_api'
|
28
|
+
|
29
|
+
module CloudmersiveOcrApiClient
|
30
|
+
class << self
|
31
|
+
# Customize default settings for the SDK using block.
|
32
|
+
# CloudmersiveOcrApiClient.configure do |config|
|
33
|
+
# config.username = "xxx"
|
34
|
+
# config.password = "xxx"
|
35
|
+
# end
|
36
|
+
# If no block given, return the default Configuration object.
|
37
|
+
def configure
|
38
|
+
if block_given?
|
39
|
+
yield(Configuration.default)
|
40
|
+
else
|
41
|
+
Configuration.default
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,144 @@
|
|
1
|
+
=begin
|
2
|
+
#ocrapi
|
3
|
+
|
4
|
+
#The powerful Optical Character Recognition (OCR) APIs let you convert scanned images of pages into recognized text.
|
5
|
+
|
6
|
+
OpenAPI spec version: v1
|
7
|
+
|
8
|
+
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
9
|
+
Swagger Codegen version: unset
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
require "uri"
|
14
|
+
|
15
|
+
module CloudmersiveOcrApiClient
|
16
|
+
class ImageOcrApi
|
17
|
+
attr_accessor :api_client
|
18
|
+
|
19
|
+
def initialize(api_client = ApiClient.default)
|
20
|
+
@api_client = api_client
|
21
|
+
end
|
22
|
+
|
23
|
+
# Convert a photo of a document into text
|
24
|
+
# Converts an uploaded photo of a document in common formats such as JPEG, PNG into text via Optical Character Recognition. This API is intended to be run on photos of documents, e.g. taken with a smartphone and supports cases where other content, such as a desk, are in the frame and the camera is crooked. If you want to OCR a scanned image, use the image/toText API call instead as it is designed for scanned images.
|
25
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
26
|
+
# @param [Hash] opts the optional parameters
|
27
|
+
# @option opts [String] :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)
|
28
|
+
# @return [ImageToTextResponse]
|
29
|
+
def image_ocr_photo_to_text(image_file, opts = {})
|
30
|
+
data, _status_code, _headers = image_ocr_photo_to_text_with_http_info(image_file, opts)
|
31
|
+
return data
|
32
|
+
end
|
33
|
+
|
34
|
+
# Convert a photo of a document into text
|
35
|
+
# Converts an uploaded photo of a document in common formats such as JPEG, PNG into text via Optical Character Recognition. This API is intended to be run on photos of documents, e.g. taken with a smartphone and supports cases where other content, such as a desk, are in the frame and the camera is crooked. If you want to OCR a scanned image, use the image/toText API call instead as it is designed for scanned images.
|
36
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
37
|
+
# @param [Hash] opts the optional parameters
|
38
|
+
# @option opts [String] :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)
|
39
|
+
# @return [Array<(ImageToTextResponse, Fixnum, Hash)>] ImageToTextResponse data, response status code and response headers
|
40
|
+
def image_ocr_photo_to_text_with_http_info(image_file, opts = {})
|
41
|
+
if @api_client.config.debugging
|
42
|
+
@api_client.config.logger.debug "Calling API: ImageOcrApi.image_ocr_photo_to_text ..."
|
43
|
+
end
|
44
|
+
# verify the required parameter 'image_file' is set
|
45
|
+
if @api_client.config.client_side_validation && image_file.nil?
|
46
|
+
fail ArgumentError, "Missing the required parameter 'image_file' when calling ImageOcrApi.image_ocr_photo_to_text"
|
47
|
+
end
|
48
|
+
# resource path
|
49
|
+
local_var_path = "/ocr/photo/toText"
|
50
|
+
|
51
|
+
# query parameters
|
52
|
+
query_params = {}
|
53
|
+
|
54
|
+
# header parameters
|
55
|
+
header_params = {}
|
56
|
+
# HTTP header 'Accept' (if needed)
|
57
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json', 'text/json', 'application/xml', 'text/xml'])
|
58
|
+
# HTTP header 'Content-Type'
|
59
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
60
|
+
header_params[:'language'] = opts[:'language'] if !opts[:'language'].nil?
|
61
|
+
|
62
|
+
# form parameters
|
63
|
+
form_params = {}
|
64
|
+
form_params["imageFile"] = image_file
|
65
|
+
|
66
|
+
# http body (model)
|
67
|
+
post_body = nil
|
68
|
+
auth_names = ['Apikey']
|
69
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
70
|
+
:header_params => header_params,
|
71
|
+
:query_params => query_params,
|
72
|
+
:form_params => form_params,
|
73
|
+
:body => post_body,
|
74
|
+
:auth_names => auth_names,
|
75
|
+
:return_type => 'ImageToTextResponse')
|
76
|
+
if @api_client.config.debugging
|
77
|
+
@api_client.config.logger.debug "API called: ImageOcrApi#image_ocr_photo_to_text\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
78
|
+
end
|
79
|
+
return data, status_code, headers
|
80
|
+
end
|
81
|
+
|
82
|
+
# Convert a scanned image into text
|
83
|
+
# Converts an uploaded image in common formats such as JPEG, PNG into text via Optical Character Recognition. This API is intended to be run on scanned documents. If you want to OCR photos (e.g. taken with a smart phone camera), be sure to use the photo/toText API instead, as it is designed to unskew the image first.
|
84
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
85
|
+
# @param [Hash] opts the optional parameters
|
86
|
+
# @option opts [String] :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)
|
87
|
+
# @option opts [String] :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).
|
88
|
+
# @return [ImageToTextResponse]
|
89
|
+
def image_ocr_post(image_file, opts = {})
|
90
|
+
data, _status_code, _headers = image_ocr_post_with_http_info(image_file, opts)
|
91
|
+
return data
|
92
|
+
end
|
93
|
+
|
94
|
+
# Convert a scanned image into text
|
95
|
+
# Converts an uploaded image in common formats such as JPEG, PNG into text via Optical Character Recognition. This API is intended to be run on scanned documents. If you want to OCR photos (e.g. taken with a smart phone camera), be sure to use the photo/toText API instead, as it is designed to unskew the image first.
|
96
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
97
|
+
# @param [Hash] opts the optional parameters
|
98
|
+
# @option opts [String] :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)
|
99
|
+
# @option opts [String] :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).
|
100
|
+
# @return [Array<(ImageToTextResponse, Fixnum, Hash)>] ImageToTextResponse data, response status code and response headers
|
101
|
+
def image_ocr_post_with_http_info(image_file, opts = {})
|
102
|
+
if @api_client.config.debugging
|
103
|
+
@api_client.config.logger.debug "Calling API: ImageOcrApi.image_ocr_post ..."
|
104
|
+
end
|
105
|
+
# verify the required parameter 'image_file' is set
|
106
|
+
if @api_client.config.client_side_validation && image_file.nil?
|
107
|
+
fail ArgumentError, "Missing the required parameter 'image_file' when calling ImageOcrApi.image_ocr_post"
|
108
|
+
end
|
109
|
+
# resource path
|
110
|
+
local_var_path = "/ocr/image/toText"
|
111
|
+
|
112
|
+
# query parameters
|
113
|
+
query_params = {}
|
114
|
+
|
115
|
+
# header parameters
|
116
|
+
header_params = {}
|
117
|
+
# HTTP header 'Accept' (if needed)
|
118
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json', 'text/json', 'application/xml', 'text/xml'])
|
119
|
+
# HTTP header 'Content-Type'
|
120
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
121
|
+
header_params[:'language'] = opts[:'language'] if !opts[:'language'].nil?
|
122
|
+
header_params[:'preprocessing'] = opts[:'preprocessing'] if !opts[:'preprocessing'].nil?
|
123
|
+
|
124
|
+
# form parameters
|
125
|
+
form_params = {}
|
126
|
+
form_params["imageFile"] = image_file
|
127
|
+
|
128
|
+
# http body (model)
|
129
|
+
post_body = nil
|
130
|
+
auth_names = ['Apikey']
|
131
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
132
|
+
:header_params => header_params,
|
133
|
+
:query_params => query_params,
|
134
|
+
:form_params => form_params,
|
135
|
+
:body => post_body,
|
136
|
+
:auth_names => auth_names,
|
137
|
+
:return_type => 'ImageToTextResponse')
|
138
|
+
if @api_client.config.debugging
|
139
|
+
@api_client.config.logger.debug "API called: ImageOcrApi#image_ocr_post\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
140
|
+
end
|
141
|
+
return data, status_code, headers
|
142
|
+
end
|
143
|
+
end
|
144
|
+
end
|
@@ -0,0 +1,85 @@
|
|
1
|
+
=begin
|
2
|
+
#ocrapi
|
3
|
+
|
4
|
+
#The powerful Optical Character Recognition (OCR) APIs let you convert scanned images of pages into recognized text.
|
5
|
+
|
6
|
+
OpenAPI spec version: v1
|
7
|
+
|
8
|
+
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
9
|
+
Swagger Codegen version: unset
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
require "uri"
|
14
|
+
|
15
|
+
module CloudmersiveOcrApiClient
|
16
|
+
class PdfOcrApi
|
17
|
+
attr_accessor :api_client
|
18
|
+
|
19
|
+
def initialize(api_client = ApiClient.default)
|
20
|
+
@api_client = api_client
|
21
|
+
end
|
22
|
+
|
23
|
+
# Converts an uploaded image in common formats such as JPEG, PNG into text via Optical Character Recognition.
|
24
|
+
#
|
25
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
26
|
+
# @param [Hash] opts the optional parameters
|
27
|
+
# @option opts [String] :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)
|
28
|
+
# @option opts [String] :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).
|
29
|
+
# @return [PdfToTextResponse]
|
30
|
+
def pdf_ocr_post(image_file, opts = {})
|
31
|
+
data, _status_code, _headers = pdf_ocr_post_with_http_info(image_file, opts)
|
32
|
+
return data
|
33
|
+
end
|
34
|
+
|
35
|
+
# Converts an uploaded image in common formats such as JPEG, PNG into text via Optical Character Recognition.
|
36
|
+
#
|
37
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
38
|
+
# @param [Hash] opts the optional parameters
|
39
|
+
# @option opts [String] :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)
|
40
|
+
# @option opts [String] :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).
|
41
|
+
# @return [Array<(PdfToTextResponse, Fixnum, Hash)>] PdfToTextResponse data, response status code and response headers
|
42
|
+
def pdf_ocr_post_with_http_info(image_file, opts = {})
|
43
|
+
if @api_client.config.debugging
|
44
|
+
@api_client.config.logger.debug "Calling API: PdfOcrApi.pdf_ocr_post ..."
|
45
|
+
end
|
46
|
+
# verify the required parameter 'image_file' is set
|
47
|
+
if @api_client.config.client_side_validation && image_file.nil?
|
48
|
+
fail ArgumentError, "Missing the required parameter 'image_file' when calling PdfOcrApi.pdf_ocr_post"
|
49
|
+
end
|
50
|
+
# resource path
|
51
|
+
local_var_path = "/ocr/pdf/toText"
|
52
|
+
|
53
|
+
# query parameters
|
54
|
+
query_params = {}
|
55
|
+
|
56
|
+
# header parameters
|
57
|
+
header_params = {}
|
58
|
+
# HTTP header 'Accept' (if needed)
|
59
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json', 'text/json', 'application/xml', 'text/xml'])
|
60
|
+
# HTTP header 'Content-Type'
|
61
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
62
|
+
header_params[:'language'] = opts[:'language'] if !opts[:'language'].nil?
|
63
|
+
header_params[:'preprocessing'] = opts[:'preprocessing'] if !opts[:'preprocessing'].nil?
|
64
|
+
|
65
|
+
# form parameters
|
66
|
+
form_params = {}
|
67
|
+
form_params["imageFile"] = image_file
|
68
|
+
|
69
|
+
# http body (model)
|
70
|
+
post_body = nil
|
71
|
+
auth_names = ['Apikey']
|
72
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
73
|
+
:header_params => header_params,
|
74
|
+
:query_params => query_params,
|
75
|
+
:form_params => form_params,
|
76
|
+
:body => post_body,
|
77
|
+
:auth_names => auth_names,
|
78
|
+
:return_type => 'PdfToTextResponse')
|
79
|
+
if @api_client.config.debugging
|
80
|
+
@api_client.config.logger.debug "API called: PdfOcrApi#pdf_ocr_post\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
81
|
+
end
|
82
|
+
return data, status_code, headers
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
@@ -0,0 +1,135 @@
|
|
1
|
+
=begin
|
2
|
+
#ocrapi
|
3
|
+
|
4
|
+
#The powerful Optical Character Recognition (OCR) APIs let you convert scanned images of pages into recognized text.
|
5
|
+
|
6
|
+
OpenAPI spec version: v1
|
7
|
+
|
8
|
+
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
9
|
+
Swagger Codegen version: unset
|
10
|
+
|
11
|
+
=end
|
12
|
+
|
13
|
+
require "uri"
|
14
|
+
|
15
|
+
module CloudmersiveOcrApiClient
|
16
|
+
class PreprocessingApi
|
17
|
+
attr_accessor :api_client
|
18
|
+
|
19
|
+
def initialize(api_client = ApiClient.default)
|
20
|
+
@api_client = api_client
|
21
|
+
end
|
22
|
+
|
23
|
+
# Detect and unrotate a document image
|
24
|
+
# Detect and unrotate an image of a document (e.g. that was scanned at an angle). Great for document scanning applications; once unskewed, this image is perfect for converting to PDF using the Convert API or optical character recognition using the OCR API.
|
25
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
26
|
+
# @param [Hash] opts the optional parameters
|
27
|
+
# @return [Object]
|
28
|
+
def preprocessing_unrotate(image_file, opts = {})
|
29
|
+
data, _status_code, _headers = preprocessing_unrotate_with_http_info(image_file, opts)
|
30
|
+
return data
|
31
|
+
end
|
32
|
+
|
33
|
+
# Detect and unrotate a document image
|
34
|
+
# Detect and unrotate an image of a document (e.g. that was scanned at an angle). Great for document scanning applications; once unskewed, this image is perfect for converting to PDF using the Convert API or optical character recognition using the OCR API.
|
35
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
36
|
+
# @param [Hash] opts the optional parameters
|
37
|
+
# @return [Array<(Object, Fixnum, Hash)>] Object data, response status code and response headers
|
38
|
+
def preprocessing_unrotate_with_http_info(image_file, opts = {})
|
39
|
+
if @api_client.config.debugging
|
40
|
+
@api_client.config.logger.debug "Calling API: PreprocessingApi.preprocessing_unrotate ..."
|
41
|
+
end
|
42
|
+
# verify the required parameter 'image_file' is set
|
43
|
+
if @api_client.config.client_side_validation && image_file.nil?
|
44
|
+
fail ArgumentError, "Missing the required parameter 'image_file' when calling PreprocessingApi.preprocessing_unrotate"
|
45
|
+
end
|
46
|
+
# resource path
|
47
|
+
local_var_path = "/ocr/preprocessing/image/unrotate"
|
48
|
+
|
49
|
+
# query parameters
|
50
|
+
query_params = {}
|
51
|
+
|
52
|
+
# header parameters
|
53
|
+
header_params = {}
|
54
|
+
# HTTP header 'Accept' (if needed)
|
55
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json', 'text/json', 'application/xml', 'text/xml'])
|
56
|
+
# HTTP header 'Content-Type'
|
57
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
58
|
+
|
59
|
+
# form parameters
|
60
|
+
form_params = {}
|
61
|
+
form_params["imageFile"] = image_file
|
62
|
+
|
63
|
+
# http body (model)
|
64
|
+
post_body = nil
|
65
|
+
auth_names = ['Apikey']
|
66
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
67
|
+
:header_params => header_params,
|
68
|
+
:query_params => query_params,
|
69
|
+
:form_params => form_params,
|
70
|
+
:body => post_body,
|
71
|
+
:auth_names => auth_names,
|
72
|
+
:return_type => 'Object')
|
73
|
+
if @api_client.config.debugging
|
74
|
+
@api_client.config.logger.debug "API called: PreprocessingApi#preprocessing_unrotate\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
75
|
+
end
|
76
|
+
return data, status_code, headers
|
77
|
+
end
|
78
|
+
|
79
|
+
# Detect and unskew a photo of a document
|
80
|
+
# Detect and unskew a photo of a document (e.g. taken on a cell phone) into a perfectly square image. Great for document scanning applications; once unskewed, this image is perfect for converting to PDF using the Convert API or optical character recognition using the OCR API.
|
81
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
82
|
+
# @param [Hash] opts the optional parameters
|
83
|
+
# @return [Object]
|
84
|
+
def preprocessing_unskew(image_file, opts = {})
|
85
|
+
data, _status_code, _headers = preprocessing_unskew_with_http_info(image_file, opts)
|
86
|
+
return data
|
87
|
+
end
|
88
|
+
|
89
|
+
# Detect and unskew a photo of a document
|
90
|
+
# Detect and unskew a photo of a document (e.g. taken on a cell phone) into a perfectly square image. Great for document scanning applications; once unskewed, this image is perfect for converting to PDF using the Convert API or optical character recognition using the OCR API.
|
91
|
+
# @param image_file Image file to perform OCR on. Common file formats such as PNG, JPEG are supported.
|
92
|
+
# @param [Hash] opts the optional parameters
|
93
|
+
# @return [Array<(Object, Fixnum, Hash)>] Object data, response status code and response headers
|
94
|
+
def preprocessing_unskew_with_http_info(image_file, opts = {})
|
95
|
+
if @api_client.config.debugging
|
96
|
+
@api_client.config.logger.debug "Calling API: PreprocessingApi.preprocessing_unskew ..."
|
97
|
+
end
|
98
|
+
# verify the required parameter 'image_file' is set
|
99
|
+
if @api_client.config.client_side_validation && image_file.nil?
|
100
|
+
fail ArgumentError, "Missing the required parameter 'image_file' when calling PreprocessingApi.preprocessing_unskew"
|
101
|
+
end
|
102
|
+
# resource path
|
103
|
+
local_var_path = "/ocr/preprocessing/image/unskew"
|
104
|
+
|
105
|
+
# query parameters
|
106
|
+
query_params = {}
|
107
|
+
|
108
|
+
# header parameters
|
109
|
+
header_params = {}
|
110
|
+
# HTTP header 'Accept' (if needed)
|
111
|
+
header_params['Accept'] = @api_client.select_header_accept(['application/json', 'text/json', 'application/xml', 'text/xml'])
|
112
|
+
# HTTP header 'Content-Type'
|
113
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
114
|
+
|
115
|
+
# form parameters
|
116
|
+
form_params = {}
|
117
|
+
form_params["imageFile"] = image_file
|
118
|
+
|
119
|
+
# http body (model)
|
120
|
+
post_body = nil
|
121
|
+
auth_names = ['Apikey']
|
122
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
123
|
+
:header_params => header_params,
|
124
|
+
:query_params => query_params,
|
125
|
+
:form_params => form_params,
|
126
|
+
:body => post_body,
|
127
|
+
:auth_names => auth_names,
|
128
|
+
:return_type => 'Object')
|
129
|
+
if @api_client.config.debugging
|
130
|
+
@api_client.config.logger.debug "API called: PreprocessingApi#preprocessing_unskew\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
131
|
+
end
|
132
|
+
return data, status_code, headers
|
133
|
+
end
|
134
|
+
end
|
135
|
+
end
|