pdfcrowd 5.1.1 → 5.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2ce783233a9cfb07981027de99484b52696c70ac36865066e263cb4524fc3aa8
-  data.tar.gz: 8af414bdd2dd8822fcd83c02cf52837baa32449c46270aa19be1c2799c503ada
+  metadata.gz: 3d5e4aae437d0c4993770eb539bcd6ec2ead0c8e825e3c3722be116d3b8547aa
+  data.tar.gz: 0dfb6bd06a801af12961879abf6f7fb2b0abe641612c53c064479fd7bd484b03
 SHA512:
-  metadata.gz: ea0a791e71eedbb2145fb754f9fb39a86583c5b5c7e4e00be87bc622a3299eca1267f1d111ee995fca6093cc5939643dda74c317aab13d067a420cf2b6e851c5
-  data.tar.gz: 110f85f489157e5db520340ca0d7ce68a14933566dbd2be2e2d5b338b4bdeb03dad99b143fbaee388a09e4c99e00477cbe51004fcb20aa14eec30145a4d2657b
+  metadata.gz: c7fbfa74285c6e038ec517bbd084b2d0022939233be6b639d9c412a4c9a40018029c7a82b86c34f2a957b5c44914ecd54b3326d5381f101764b9055088fdc86d
+  data.tar.gz: b076d3ea8b2766b5668f36fcafc895e597e47beb0a64c0237ace8ff25e121f934a0ec54c53456578f60b39611a2c2d29617fc805ab5a397b87d8f0fd8f7b7161

data/lib/pdfcrowd.rb

@@ -530,7 +530,7 @@ end
 module Pdfcrowd
     HOST = ENV["PDFCROWD_HOST"] || 'api.pdfcrowd.com'
     MULTIPART_BOUNDARY = '----------ThIs_Is_tHe_bOUnDary_$'
-    CLIENT_VERSION = '5.1.1'
+    CLIENT_VERSION = '5.4.0'
 
     class ConnectionHelper
         def initialize(user_name, api_key)
@@ -541,7 +541,7 @@ module Pdfcrowd
 
             setProxy(nil, nil, nil, nil)
             setUseHttp(false)
-            setUserAgent('pdfcrowd_ruby_client/5.1.1 (https://pdfcrowd.com)')
+            setUserAgent('pdfcrowd_ruby_client/5.4.0 (https://pdfcrowd.com)')
 
             @retry_count = 1
             @converter_version = '20.10'
@@ -626,7 +626,7 @@ module Pdfcrowd
             body << 'Content-Disposition: form-data; name="%s"; filename="%s"' % [name, file_name]
             body << 'Content-Type: application/octet-stream'
             body << ''
-            body << data
+            body << data.force_encoding('UTF-8')
         end
 
         def self.encode_multipart_post_data(fields, files, raw_data)
@@ -735,7 +735,7 @@ module Pdfcrowd
     def self.create_invalid_value_message(value, field, converter, hint, id)
         message = "Invalid value '%s' for %s." % [value, field]
         message += " " + hint if hint
-        return message + " " + "Details: https://www.pdfcrowd.com/doc/api/%s/ruby/#%s" % [converter, id]
+        return message + " " + "Details: https://www.pdfcrowd.com/doc/api/%s/ruby/ref/#%s" % [converter, id]
     end
 
 # generated code
@@ -933,6 +933,15 @@ module Pdfcrowd
             end
         end
 
+        # Set the file name of the main HTML document stored in the input archive. If not specified, the first HTML file in the archive is used for conversion. Use this method if the input archive contains multiple HTML documents.
+        #
+        # * +filename+ - The file name.
+        # * *Returns* - The converter object.
+        def setZipMainFilename(filename)
+            @fields['zip_main_filename'] = filename
+            self
+        end
+
         # Set the output page size.
         #
         # * +size+ - Allowed values are A0, A1, A2, A3, A4, A5, A6, Letter.
@@ -1174,7 +1183,7 @@ module Pdfcrowd
             self
         end
 
-        # Load an HTML code from the specified URL and use it as the page header. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals Arabic numerals are used by default. Roman numerals can be generated by the roman and roman-lowercase values Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL, allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
+        # Load an HTML code from the specified URL and use it as the page header. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals. Allowed values: arabic - Arabic numerals, they are used by default roman - Roman numerals eastern-arabic - Eastern Arabic numerals bengali - Bengali numerals devanagari - Devanagari numerals thai - Thai numerals east-asia - Chinese, Vietnamese, Japanese and Korean numerals chinese-formal - Chinese formal numerals Please contact us if you need another type of numerals. Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL. Allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
         #
         # * +url+ - The supported protocols are http:// and https://.
         # * *Returns* - The converter object.
@@ -1187,7 +1196,7 @@ module Pdfcrowd
             self
         end
 
-        # Use the specified HTML code as the page header. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals Arabic numerals are used by default. Roman numerals can be generated by the roman and roman-lowercase values Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL, allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
+        # Use the specified HTML code as the page header. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals. Allowed values: arabic - Arabic numerals, they are used by default roman - Roman numerals eastern-arabic - Eastern Arabic numerals bengali - Bengali numerals devanagari - Devanagari numerals thai - Thai numerals east-asia - Chinese, Vietnamese, Japanese and Korean numerals chinese-formal - Chinese formal numerals Please contact us if you need another type of numerals. Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL. Allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
         #
         # * +html+ - The string must not be empty.
         # * *Returns* - The converter object.
@@ -1213,7 +1222,16 @@ module Pdfcrowd
             self
         end
 
-        # Load an HTML code from the specified URL and use it as the page footer. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals Arabic numerals are used by default. Roman numerals can be generated by the roman and roman-lowercase values Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL, allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
+        # Set the file name of the header HTML document stored in the input archive. Use this method if the input archive contains multiple HTML documents.
+        #
+        # * +filename+ - The file name.
+        # * *Returns* - The converter object.
+        def setZipHeaderFilename(filename)
+            @fields['zip_header_filename'] = filename
+            self
+        end
+
+        # Load an HTML code from the specified URL and use it as the page footer. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals. Allowed values: arabic - Arabic numerals, they are used by default roman - Roman numerals eastern-arabic - Eastern Arabic numerals bengali - Bengali numerals devanagari - Devanagari numerals thai - Thai numerals east-asia - Chinese, Vietnamese, Japanese and Korean numerals chinese-formal - Chinese formal numerals Please contact us if you need another type of numerals. Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL. Allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
         #
         # * +url+ - The supported protocols are http:// and https://.
         # * *Returns* - The converter object.
@@ -1226,7 +1244,7 @@ module Pdfcrowd
             self
         end
 
-        # Use the specified HTML as the page footer. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals Arabic numerals are used by default. Roman numerals can be generated by the roman and roman-lowercase values Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL, allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
+        # Use the specified HTML as the page footer. The following classes can be used in the HTML. The content of the respective elements will be expanded as follows: pdfcrowd-page-count - the total page count of printed pages pdfcrowd-page-number - the current page number pdfcrowd-source-url - the source URL of a converted document The following attributes can be used: data-pdfcrowd-number-format - specifies the type of the used numerals. Allowed values: arabic - Arabic numerals, they are used by default roman - Roman numerals eastern-arabic - Eastern Arabic numerals bengali - Bengali numerals devanagari - Devanagari numerals thai - Thai numerals east-asia - Chinese, Vietnamese, Japanese and Korean numerals chinese-formal - Chinese formal numerals Please contact us if you need another type of numerals. Example: <span class='pdfcrowd-page-number' data-pdfcrowd-number-format='roman'></span> data-pdfcrowd-placement - specifies where to place the source URL. Allowed values: The URL is inserted to the content Example: <span class='pdfcrowd-source-url'></span> will produce <span>http://example.com</span> href - the URL is set to the href attribute Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href'>Link to source</a> will produce <a href='http://example.com'>Link to source</a> href-and-content - the URL is set to the href attribute and to the content Example: <a class='pdfcrowd-source-url' data-pdfcrowd-placement='href-and-content'></a> will produce <a href='http://example.com'>http://example.com</a>
         #
         # * +html+ - The string must not be empty.
         # * *Returns* - The converter object.
@@ -1252,6 +1270,15 @@ module Pdfcrowd
             self
         end
 
+        # Set the file name of the footer HTML document stored in the input archive. Use this method if the input archive contains multiple HTML documents.
+        #
+        # * +filename+ - The file name.
+        # * *Returns* - The converter object.
+        def setZipFooterFilename(filename)
+            @fields['zip_footer_filename'] = filename
+            self
+        end
+
         # Disable horizontal page margins for header and footer. The header/footer contents width will be equal to the physical page width.
         #
         # * +value+ - Set to true to disable horizontal margins for header and footer.
@@ -1462,6 +1489,15 @@ module Pdfcrowd
             self
         end
 
+        # Use a mobile user agent.
+        #
+        # * +value+ - Set to true to use a mobile user agent.
+        # * *Returns* - The converter object.
+        def setUseMobileUserAgent(value)
+            @fields['use_mobile_user_agent'] = value
+            self
+        end
+
         # Specifies how iframes are handled.
         #
         # * +iframes+ - Allowed values are all, same-origin, none.
@@ -1641,7 +1677,7 @@ module Pdfcrowd
             self
         end
 
-        # Specify the DOM handling when only a part of the document is converted.
+        # Specify the DOM handling when only a part of the document is converted. This can affect the CSS rules used.
         #
         # * +mode+ - Allowed values are cut-out, remove-siblings, hide-siblings.
         # * *Returns* - The converter object.
@@ -1680,7 +1716,7 @@ module Pdfcrowd
             self
         end
 
-        # Set the viewport height in pixels. The viewport is the user's visible area of the page.
+        # Set the viewport height in pixels. The viewport is the user's visible area of the page. If the input HTML uses lazily loaded images, try using a large value that covers the entire height of the HTML, e.g. 100000.
         #
         # * +height+ - Must be a positive integer number.
         # * *Returns* - The converter object.
@@ -1696,7 +1732,7 @@ module Pdfcrowd
         # Set the viewport size. The viewport is the user's visible area of the page.
         #
         # * +width+ - Set the viewport width in pixels. The viewport is the user's visible area of the page. The value must be in the range 96-65000.
-        # * +height+ - Set the viewport height in pixels. The viewport is the user's visible area of the page. Must be a positive integer number.
+        # * +height+ - Set the viewport height in pixels. The viewport is the user's visible area of the page. If the input HTML uses lazily loaded images, try using a large value that covers the entire height of the HTML, e.g. 100000. Must be a positive integer number.
         # * *Returns* - The converter object.
         def setViewport(width, height)
             setViewportWidth(width)
@@ -1881,6 +1917,15 @@ module Pdfcrowd
             self
         end
 
+        # Extract meta tags (author, keywords and description) from the input HTML and use them in the output PDF.
+        #
+        # * +value+ - Set to true to extract meta tags.
+        # * *Returns* - The converter object.
+        def setExtractMetaTags(value)
+            @fields['extract_meta_tags'] = value
+            self
+        end
+
         # Specify the page layout to be used when the document is opened.
         #
         # * +layout+ - Allowed values are single-page, one-column, two-column-left, two-column-right.
@@ -2101,7 +2146,7 @@ module Pdfcrowd
         end
 
         # Get the number of conversion credits available in your account.
-        # This method can only be called after a call to one of the convertXYZ methods.
+        # This method can only be called after a call to one of the convertXtoY methods.
         # The returned value can differ from the actual count if you run parallel conversions.
         # The special value 999999 is returned if the information is not available.
         # * *Returns* - The number of credits.
@@ -2287,7 +2332,7 @@ module Pdfcrowd
             self
         end
 
-        # Set a custom user agent HTTP header. It can be useful if you are behind some proxy or firewall.
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
         #
         # * +agent+ - The user agent string.
         # * *Returns* - The converter object.
@@ -2308,9 +2353,9 @@ module Pdfcrowd
             self
         end
 
-        # Specifies the number of retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
         #
-        # * +count+ - Number of retries wanted.
+        # * +count+ - Number of retries.
         # * *Returns* - The converter object.
         def setRetryCount(count)
             @helper.setRetryCount(count)
@@ -2525,6 +2570,15 @@ module Pdfcrowd
             end
         end
 
+        # Set the file name of the main HTML document stored in the input archive. If not specified, the first HTML file in the archive is used for conversion. Use this method if the input archive contains multiple HTML documents.
+        #
+        # * +filename+ - The file name.
+        # * *Returns* - The converter object.
+        def setZipMainFilename(filename)
+            @fields['zip_main_filename'] = filename
+            self
+        end
+
         # Use the print version of the page if available (@media print).
         #
         # * +value+ - Set to true to use the print version of the page.
@@ -2570,6 +2624,15 @@ module Pdfcrowd
             self
         end
 
+        # Use a mobile user agent.
+        #
+        # * +value+ - Set to true to use a mobile user agent.
+        # * *Returns* - The converter object.
+        def setUseMobileUserAgent(value)
+            @fields['use_mobile_user_agent'] = value
+            self
+        end
+
         # Specifies how iframes are handled.
         #
         # * +iframes+ - Allowed values are all, same-origin, none.
@@ -2749,7 +2812,7 @@ module Pdfcrowd
             self
         end
 
-        # Specify the DOM handling when only a part of the document is converted.
+        # Specify the DOM handling when only a part of the document is converted. This can affect the CSS rules used.
         #
         # * +mode+ - Allowed values are cut-out, remove-siblings, hide-siblings.
         # * *Returns* - The converter object.
@@ -2919,7 +2982,7 @@ module Pdfcrowd
         end
 
         # Get the number of conversion credits available in your account.
-        # This method can only be called after a call to one of the convertXYZ methods.
+        # This method can only be called after a call to one of the convertXtoY methods.
         # The returned value can differ from the actual count if you run parallel conversions.
         # The special value 999999 is returned if the information is not available.
         # * *Returns* - The number of credits.
@@ -3031,7 +3094,7 @@ module Pdfcrowd
             self
         end
 
-        # Set a custom user agent HTTP header. It can be useful if you are behind some proxy or firewall.
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
         #
         # * +agent+ - The user agent string.
         # * *Returns* - The converter object.
@@ -3052,9 +3115,9 @@ module Pdfcrowd
             self
         end
 
-        # Specifies the number of retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
         #
-        # * +count+ - Number of retries wanted.
+        # * +count+ - Number of retries.
         # * *Returns* - The converter object.
         def setRetryCount(count)
             @helper.setRetryCount(count)
@@ -3295,7 +3358,7 @@ module Pdfcrowd
         end
 
         # Get the number of conversion credits available in your account.
-        # This method can only be called after a call to one of the convertXYZ methods.
+        # This method can only be called after a call to one of the convertXtoY methods.
         # The returned value can differ from the actual count if you run parallel conversions.
         # The special value 999999 is returned if the information is not available.
         # * *Returns* - The number of credits.
@@ -3385,7 +3448,7 @@ module Pdfcrowd
             self
         end
 
-        # Set a custom user agent HTTP header. It can be useful if you are behind some proxy or firewall.
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
         #
         # * +agent+ - The user agent string.
         # * *Returns* - The converter object.
@@ -3406,9 +3469,9 @@ module Pdfcrowd
             self
         end
 
-        # Specifies the number of retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
         #
-        # * +count+ - Number of retries wanted.
+        # * +count+ - Number of retries.
         # * *Returns* - The converter object.
         def setRetryCount(count)
             @helper.setRetryCount(count)
@@ -3501,6 +3564,15 @@ module Pdfcrowd
             self
         end
 
+        # Password to open the encrypted PDF file.
+        #
+        # * +password+ - The input PDF password.
+        # * *Returns* - The converter object.
+        def setInputPdfPassword(password)
+            @fields['input_pdf_password'] = password
+            self
+        end
+
         # Apply the first page of the watermark PDF to every page of the output PDF.
         #
         # * +watermark+ - The file path to a local watermark PDF file. The file must exist and not be empty.
@@ -3668,6 +3740,55 @@ module Pdfcrowd
             self
         end
 
+        # Set the title of the PDF.
+        #
+        # * +title+ - The title.
+        # * *Returns* - The converter object.
+        def setTitle(title)
+            @fields['title'] = title
+            self
+        end
+
+        # Set the subject of the PDF.
+        #
+        # * +subject+ - The subject.
+        # * *Returns* - The converter object.
+        def setSubject(subject)
+            @fields['subject'] = subject
+            self
+        end
+
+        # Set the author of the PDF.
+        #
+        # * +author+ - The author.
+        # * *Returns* - The converter object.
+        def setAuthor(author)
+            @fields['author'] = author
+            self
+        end
+
+        # Associate keywords with the document.
+        #
+        # * +keywords+ - The string with the keywords.
+        # * *Returns* - The converter object.
+        def setKeywords(keywords)
+            @fields['keywords'] = keywords
+            self
+        end
+
+        # Use metadata (title, subject, author and keywords) from the n-th input PDF.
+        #
+        # * +index+ - Set the index of the input PDF file from which to use the metadata. 0 means no metadata. Must be a positive integer number or 0.
+        # * *Returns* - The converter object.
+        def setUseMetadataFrom(index)
+            if (!(Integer(index) >= 0))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(index, "setUseMetadataFrom", "pdf-to-pdf", "Must be a positive integer number or 0.", "set_use_metadata_from"), 470);
+            end
+            
+            @fields['use_metadata_from'] = index
+            self
+        end
+
         # Specify the page layout to be used when the document is opened.
         #
         # * +layout+ - Allowed values are single-page, one-column, two-column-left, two-column-right.
@@ -3812,7 +3933,7 @@ module Pdfcrowd
         end
 
         # Get the number of conversion credits available in your account.
-        # This method can only be called after a call to one of the convertXYZ methods.
+        # This method can only be called after a call to one of the convertXtoY methods.
         # The returned value can differ from the actual count if you run parallel conversions.
         # The special value 999999 is returned if the information is not available.
         # * *Returns* - The number of credits.
@@ -3882,7 +4003,7 @@ module Pdfcrowd
             self
         end
 
-        # Set a custom user agent HTTP header. It can be useful if you are behind some proxy or firewall.
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
         #
         # * +agent+ - The user agent string.
         # * *Returns* - The converter object.
@@ -3903,9 +4024,9 @@ module Pdfcrowd
             self
         end
 
-        # Specifies the number of retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
         #
-        # * +count+ - Number of retries wanted.
+        # * +count+ - Number of retries.
         # * *Returns* - The converter object.
         def setRetryCount(count)
             @helper.setRetryCount(count)
@@ -4133,7 +4254,7 @@ module Pdfcrowd
         end
 
         # Get the number of conversion credits available in your account.
-        # This method can only be called after a call to one of the convertXYZ methods.
+        # This method can only be called after a call to one of the convertXtoY methods.
         # The returned value can differ from the actual count if you run parallel conversions.
         # The special value 999999 is returned if the information is not available.
         # * *Returns* - The number of credits.
@@ -4223,7 +4344,464 @@ module Pdfcrowd
             self
         end
 
-        # Set a custom user agent HTTP header. It can be useful if you are behind some proxy or firewall.
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
+        #
+        # * +agent+ - The user agent string.
+        # * *Returns* - The converter object.
+        def setUserAgent(agent)
+            @helper.setUserAgent(agent)
+            self
+        end
+
+        # Specifies an HTTP proxy that the API client library will use to connect to the internet.
+        #
+        # * +host+ - The proxy hostname.
+        # * +port+ - The proxy port.
+        # * +user_name+ - The username.
+        # * +password+ - The password.
+        # * *Returns* - The converter object.
+        def setProxy(host, port, user_name, password)
+            @helper.setProxy(host, port, user_name, password)
+            self
+        end
+
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        #
+        # * +count+ - Number of retries.
+        # * *Returns* - The converter object.
+        def setRetryCount(count)
+            @helper.setRetryCount(count)
+            self
+        end
+
+    end
+
+    # Conversion from PDF to HTML.
+    class PdfToHtmlClient
+        # Constructor for the Pdfcrowd API client.
+        #
+        # * +user_name+ - Your username at Pdfcrowd.
+        # * +api_key+ - Your API key.
+        def initialize(user_name, api_key)
+            @helper = ConnectionHelper.new(user_name, api_key)
+            @fields = {
+                'input_format'=>'pdf',
+                'output_format'=>'html'
+            }
+            @file_id = 1
+            @files = {}
+            @raw_data = {}
+        end
+
+        # Convert a PDF.
+        #
+        # * +url+ - The address of the PDF to convert. The supported protocols are http:// and https://.
+        # * *Returns* - Byte array containing the conversion output.
+        def convertUrl(url)
+            unless /(?i)^https?:\/\/.*$/.match(url)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(url, "convertUrl", "pdf-to-html", "The supported protocols are http:// and https://.", "convert_url"), 470);
+            end
+            
+            @fields['url'] = url
+            @helper.post(@fields, @files, @raw_data)
+        end
+
+        # Convert a PDF and write the result to an output stream.
+        #
+        # * +url+ - The address of the PDF to convert. The supported protocols are http:// and https://.
+        # * +out_stream+ - The output stream that will contain the conversion output.
+        def convertUrlToStream(url, out_stream)
+            unless /(?i)^https?:\/\/.*$/.match(url)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(url, "convertUrlToStream::url", "pdf-to-html", "The supported protocols are http:// and https://.", "convert_url_to_stream"), 470);
+            end
+            
+            @fields['url'] = url
+            @helper.post(@fields, @files, @raw_data, out_stream)
+        end
+
+        # Convert a PDF and write the result to a local file.
+        #
+        # * +url+ - The address of the PDF to convert. The supported protocols are http:// and https://.
+        # * +file_path+ - The output file path. The string must not be empty. The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.
+        def convertUrlToFile(url, file_path)
+            if (!(!file_path.nil? && !file_path.empty?))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertUrlToFile::file_path", "pdf-to-html", "The string must not be empty.", "convert_url_to_file"), 470);
+            end
+            
+            if (!(isOutputTypeValid(file_path)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertUrlToFile::file_path", "pdf-to-html", "The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.", "convert_url_to_file"), 470);
+            end
+            
+            output_file = open(file_path, "wb")
+            begin
+                convertUrlToStream(url, output_file)
+                output_file.close()
+            rescue Error => why
+                output_file.close()
+                FileUtils.rm(file_path)
+                raise
+            end
+        end
+
+        # Convert a local file.
+        #
+        # * +file+ - The path to a local file to convert. The file must exist and not be empty.
+        # * *Returns* - Byte array containing the conversion output.
+        def convertFile(file)
+            if (!(File.file?(file) && !File.zero?(file)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file, "convertFile", "pdf-to-html", "The file must exist and not be empty.", "convert_file"), 470);
+            end
+            
+            @files['file'] = file
+            @helper.post(@fields, @files, @raw_data)
+        end
+
+        # Convert a local file and write the result to an output stream.
+        #
+        # * +file+ - The path to a local file to convert. The file must exist and not be empty.
+        # * +out_stream+ - The output stream that will contain the conversion output.
+        def convertFileToStream(file, out_stream)
+            if (!(File.file?(file) && !File.zero?(file)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file, "convertFileToStream::file", "pdf-to-html", "The file must exist and not be empty.", "convert_file_to_stream"), 470);
+            end
+            
+            @files['file'] = file
+            @helper.post(@fields, @files, @raw_data, out_stream)
+        end
+
+        # Convert a local file and write the result to a local file.
+        #
+        # * +file+ - The path to a local file to convert. The file must exist and not be empty.
+        # * +file_path+ - The output file path. The string must not be empty. The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.
+        def convertFileToFile(file, file_path)
+            if (!(!file_path.nil? && !file_path.empty?))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertFileToFile::file_path", "pdf-to-html", "The string must not be empty.", "convert_file_to_file"), 470);
+            end
+            
+            if (!(isOutputTypeValid(file_path)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertFileToFile::file_path", "pdf-to-html", "The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.", "convert_file_to_file"), 470);
+            end
+            
+            output_file = open(file_path, "wb")
+            begin
+                convertFileToStream(file, output_file)
+                output_file.close()
+            rescue Error => why
+                output_file.close()
+                FileUtils.rm(file_path)
+                raise
+            end
+        end
+
+        # Convert raw data.
+        #
+        # * +data+ - The raw content to be converted.
+        # * *Returns* - Byte array with the output.
+        def convertRawData(data)
+            @raw_data['file'] = data
+            @helper.post(@fields, @files, @raw_data)
+        end
+
+        # Convert raw data and write the result to an output stream.
+        #
+        # * +data+ - The raw content to be converted.
+        # * +out_stream+ - The output stream that will contain the conversion output.
+        def convertRawDataToStream(data, out_stream)
+            @raw_data['file'] = data
+            @helper.post(@fields, @files, @raw_data, out_stream)
+        end
+
+        # Convert raw data to a file.
+        #
+        # * +data+ - The raw content to be converted.
+        # * +file_path+ - The output file path. The string must not be empty. The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.
+        def convertRawDataToFile(data, file_path)
+            if (!(!file_path.nil? && !file_path.empty?))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertRawDataToFile::file_path", "pdf-to-html", "The string must not be empty.", "convert_raw_data_to_file"), 470);
+            end
+            
+            if (!(isOutputTypeValid(file_path)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertRawDataToFile::file_path", "pdf-to-html", "The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.", "convert_raw_data_to_file"), 470);
+            end
+            
+            output_file = open(file_path, "wb")
+            begin
+                convertRawDataToStream(data, output_file)
+                output_file.close()
+            rescue Error => why
+                output_file.close()
+                FileUtils.rm(file_path)
+                raise
+            end
+        end
+
+        # Convert the contents of an input stream.
+        #
+        # * +in_stream+ - The input stream with source data.
+        # * *Returns* - Byte array containing the conversion output.
+        def convertStream(in_stream)
+            @raw_data['stream'] = in_stream.read
+            @helper.post(@fields, @files, @raw_data)
+        end
+
+        # Convert the contents of an input stream and write the result to an output stream.
+        #
+        # * +in_stream+ - The input stream with source data.
+        # * +out_stream+ - The output stream that will contain the conversion output.
+        def convertStreamToStream(in_stream, out_stream)
+            @raw_data['stream'] = in_stream.read
+            @helper.post(@fields, @files, @raw_data, out_stream)
+        end
+
+        # Convert the contents of an input stream and write the result to a local file.
+        #
+        # * +in_stream+ - The input stream with source data.
+        # * +file_path+ - The output file path. The string must not be empty. The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.
+        def convertStreamToFile(in_stream, file_path)
+            if (!(!file_path.nil? && !file_path.empty?))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertStreamToFile::file_path", "pdf-to-html", "The string must not be empty.", "convert_stream_to_file"), 470);
+            end
+            
+            if (!(isOutputTypeValid(file_path)))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(file_path, "convertStreamToFile::file_path", "pdf-to-html", "The converter generates an HTML or ZIP file. If ZIP file is generated, the file path must have a ZIP or zip extension.", "convert_stream_to_file"), 470);
+            end
+            
+            output_file = open(file_path, "wb")
+            begin
+                convertStreamToStream(in_stream, output_file)
+                output_file.close()
+            rescue Error => why
+                output_file.close()
+                FileUtils.rm(file_path)
+                raise
+            end
+        end
+
+        # Password to open the encrypted PDF file.
+        #
+        # * +password+ - The input PDF password.
+        # * *Returns* - The converter object.
+        def setPdfPassword(password)
+            @fields['pdf_password'] = password
+            self
+        end
+
+        # Set the scaling factor (zoom) for the main page area.
+        #
+        # * +factor+ - The percentage value. Must be a positive integer number.
+        # * *Returns* - The converter object.
+        def setScaleFactor(factor)
+            if (!(Integer(factor) > 0))
+                raise Error.new(Pdfcrowd.create_invalid_value_message(factor, "setScaleFactor", "pdf-to-html", "Must be a positive integer number.", "set_scale_factor"), 470);
+            end
+            
+            @fields['scale_factor'] = factor
+            self
+        end
+
+        # Set the page range to print.
+        #
+        # * +pages+ - A comma separated list of page numbers or ranges.
+        # * *Returns* - The converter object.
+        def setPrintPageRange(pages)
+            unless /^(?:\s*(?:\d+|(?:\d*\s*\-\s*\d+)|(?:\d+\s*\-\s*\d*))\s*,\s*)*\s*(?:\d+|(?:\d*\s*\-\s*\d+)|(?:\d+\s*\-\s*\d*))\s*$/.match(pages)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(pages, "setPrintPageRange", "pdf-to-html", "A comma separated list of page numbers or ranges.", "set_print_page_range"), 470);
+            end
+            
+            @fields['print_page_range'] = pages
+            self
+        end
+
+        # Specifies where the images are stored.
+        #
+        # * +mode+ - The image storage mode. Allowed values are embed, separate.
+        # * *Returns* - The converter object.
+        def setImageMode(mode)
+            unless /(?i)^(embed|separate)$/.match(mode)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(mode, "setImageMode", "pdf-to-html", "Allowed values are embed, separate.", "set_image_mode"), 470);
+            end
+            
+            @fields['image_mode'] = mode
+            self
+        end
+
+        # Specifies where the style sheets are stored.
+        #
+        # * +mode+ - The style sheet storage mode. Allowed values are embed, separate.
+        # * *Returns* - The converter object.
+        def setCssMode(mode)
+            unless /(?i)^(embed|separate)$/.match(mode)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(mode, "setCssMode", "pdf-to-html", "Allowed values are embed, separate.", "set_css_mode"), 470);
+            end
+            
+            @fields['css_mode'] = mode
+            self
+        end
+
+        # Specifies where the fonts are stored.
+        #
+        # * +mode+ - The font storage mode. Allowed values are embed, separate.
+        # * *Returns* - The converter object.
+        def setFontMode(mode)
+            unless /(?i)^(embed|separate)$/.match(mode)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(mode, "setFontMode", "pdf-to-html", "Allowed values are embed, separate.", "set_font_mode"), 470);
+            end
+            
+            @fields['font_mode'] = mode
+            self
+        end
+
+        # A helper method to determine if the output file is a zip archive. The output of the conversion may be either an HTML file or a zip file containing the HTML and its external assets.
+        # * *Returns* - True if the conversion output is a zip file, otherwise False.
+        def isZippedOutput()
+            @fields.fetch('image_mode', '') == 'separate' || @fields.fetch('css_mode', '') == 'separate' || @fields.fetch('font_mode', '') == 'separate' || @fields.fetch('force_zip', false) == true
+        end
+
+        # Enforces the zip output format.
+        #
+        # * +value+ - Set to true to get the output as a zip archive.
+        # * *Returns* - The converter object.
+        def setForceZip(value)
+            @fields['force_zip'] = value
+            self
+        end
+
+        # Set the HTML title. The title from the input PDF is used by default.
+        #
+        # * +title+ - The HTML title.
+        # * *Returns* - The converter object.
+        def setTitle(title)
+            @fields['title'] = title
+            self
+        end
+
+        # Set the HTML subject. The subject from the input PDF is used by default.
+        #
+        # * +subject+ - The HTML subject.
+        # * *Returns* - The converter object.
+        def setSubject(subject)
+            @fields['subject'] = subject
+            self
+        end
+
+        # Set the HTML author. The author from the input PDF is used by default.
+        #
+        # * +author+ - The HTML author.
+        # * *Returns* - The converter object.
+        def setAuthor(author)
+            @fields['author'] = author
+            self
+        end
+
+        # Associate keywords with the HTML document. Keywords from the input PDF are used by default.
+        #
+        # * +keywords+ - The string containing the keywords.
+        # * *Returns* - The converter object.
+        def setKeywords(keywords)
+            @fields['keywords'] = keywords
+            self
+        end
+
+        # Turn on the debug logging. Details about the conversion are stored in the debug log. The URL of the log can be obtained from the getDebugLogUrl method or available in conversion statistics.
+        #
+        # * +value+ - Set to true to enable the debug logging.
+        # * *Returns* - The converter object.
+        def setDebugLog(value)
+            @fields['debug_log'] = value
+            self
+        end
+
+        # Get the URL of the debug log for the last conversion.
+        # * *Returns* - The link to the debug log.
+        def getDebugLogUrl()
+            return @helper.getDebugLogUrl()
+        end
+
+        # Get the number of conversion credits available in your account.
+        # This method can only be called after a call to one of the convertXtoY methods.
+        # The returned value can differ from the actual count if you run parallel conversions.
+        # The special value 999999 is returned if the information is not available.
+        # * *Returns* - The number of credits.
+        def getRemainingCreditCount()
+            return @helper.getRemainingCreditCount()
+        end
+
+        # Get the number of credits consumed by the last conversion.
+        # * *Returns* - The number of credits.
+        def getConsumedCreditCount()
+            return @helper.getConsumedCreditCount()
+        end
+
+        # Get the job id.
+        # * *Returns* - The unique job identifier.
+        def getJobId()
+            return @helper.getJobId()
+        end
+
+        # Get the total number of pages in the output document.
+        # * *Returns* - The page count.
+        def getPageCount()
+            return @helper.getPageCount()
+        end
+
+        # Get the size of the output in bytes.
+        # * *Returns* - The count of bytes.
+        def getOutputSize()
+            return @helper.getOutputSize()
+        end
+
+        # Get the version details.
+        # * *Returns* - API version, converter version, and client version.
+        def getVersion()
+            return "client " + CLIENT_VERSION + ", API v2, converter " + @helper.getConverterVersion()
+        end
+
+        # Tag the conversion with a custom value. The tag is used in conversion statistics. A value longer than 32 characters is cut off.
+        #
+        # * +tag+ - A string with the custom tag.
+        # * *Returns* - The converter object.
+        def setTag(tag)
+            @fields['tag'] = tag
+            self
+        end
+
+        # A proxy server used by Pdfcrowd conversion process for accessing the source URLs with HTTP scheme. It can help to circumvent regional restrictions or provide limited access to your intranet.
+        #
+        # * +proxy+ - The value must have format DOMAIN_OR_IP_ADDRESS:PORT.
+        # * *Returns* - The converter object.
+        def setHttpProxy(proxy)
+            unless /(?i)^([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z0-9]{1,}:\d+$/.match(proxy)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(proxy, "setHttpProxy", "pdf-to-html", "The value must have format DOMAIN_OR_IP_ADDRESS:PORT.", "set_http_proxy"), 470);
+            end
+            
+            @fields['http_proxy'] = proxy
+            self
+        end
+
+        # A proxy server used by Pdfcrowd conversion process for accessing the source URLs with HTTPS scheme. It can help to circumvent regional restrictions or provide limited access to your intranet.
+        #
+        # * +proxy+ - The value must have format DOMAIN_OR_IP_ADDRESS:PORT.
+        # * *Returns* - The converter object.
+        def setHttpsProxy(proxy)
+            unless /(?i)^([a-z0-9]+(-[a-z0-9]+)*\.)+[a-z0-9]{1,}:\d+$/.match(proxy)
+                raise Error.new(Pdfcrowd.create_invalid_value_message(proxy, "setHttpsProxy", "pdf-to-html", "The value must have format DOMAIN_OR_IP_ADDRESS:PORT.", "set_https_proxy"), 470);
+            end
+            
+            @fields['https_proxy'] = proxy
+            self
+        end
+
+        # Specifies if the client communicates over HTTP or HTTPS with Pdfcrowd API.
+        # Warning: Using HTTP is insecure as data sent over HTTP is not encrypted. Enable this option only if you know what you are doing.
+        #
+        # * +value+ - Set to true to use HTTP.
+        # * *Returns* - The converter object.
+        def setUseHttp(value)
+            @helper.setUseHttp(value)
+            self
+        end
+
+        # Set a custom user agent HTTP header. It can be useful if you are behind a proxy or a firewall.
         #
         # * +agent+ - The user agent string.
         # * *Returns* - The converter object.
@@ -4244,15 +4822,21 @@ module Pdfcrowd
             self
         end
 
-        # Specifies the number of retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
+        # Specifies the number of automatic retries when the 502 HTTP status code is received. The 502 status code indicates a temporary network issue. This feature can be disabled by setting to 0.
         #
-        # * +count+ - Number of retries wanted.
+        # * +count+ - Number of retries.
         # * *Returns* - The converter object.
         def setRetryCount(count)
             @helper.setRetryCount(count)
             self
         end
 
+        private
+
+        def isOutputTypeValid(file_path)
+            extension = File.extname(file_path).downcase
+            (extension == '.zip') == isZippedOutput()
+        end
     end
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdfcrowd
 version: !ruby/object:Gem::Version
-  version: 5.1.1
+  version: 5.4.0
 platform: ruby
 authors:
 - Pdfcrowd Team
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-05-12 00:00:00.000000000 Z
+date: 2022-02-08 00:00:00.000000000 Z
 dependencies: []
 description: The Pdfcrowd API lets you easily convert between HTML, PDF and various
   image formats.