pdfium 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4f0a20b6dc310130f33f3fe36394b4cadc0bbf10
-  data.tar.gz: 5af66006fa995e366e59c4798e8585e20ca04914
+  metadata.gz: 90ada68ee9bb62299a1efee382547acc23f87284
+  data.tar.gz: cfde2cce4a21b04710aac0609cca271424ab25ce
 SHA512:
-  metadata.gz: bedd33815a4a6c4761a47b4c2f3679093c641554789cfa236365a2c6681352bca6c0e43b0a2a7b12ffdd1c29839c78d71cd3280bbc5e17afec52749e6f208677
-  data.tar.gz: 966a05f3938c7433a4ba925a7c8a07fe0093a02639f7272b11e38876a78879a9b06abb48aa213a2e92e203152e635d104faafda464c11216ae804890ef1068db
+  metadata.gz: fbb57c9b0da747032ab1969b33c0c3dbe3d1848d960cc5021bb49abb7544c953c323e47cac359788196679ce0cbbf65bdcb6d8bfec1f01ed8f4bd50cf4129366
+  data.tar.gz: 0f13a3d72c9f5577de9d6d479f0d48e019fe1daf640528dd09259ad8ae2b156b43d97f2f72d320853d6367b22b3f7ee66a6e3d0105aee2acd48d25b23f149e17

data/.gitignore

@@ -1,4 +1,7 @@
 .bundle
+.yardoc
+doc
+pkg
 Gemfile.lock
 *.bundle
 *.so

data/.yardopts

@@ -0,0 +1,3 @@
+lib/pdfium*
+ext/pdfium_ext/*.cc
+--no-private

data/README.md

@@ -6,6 +6,33 @@ It currently has only very rudimantary PDF editing capabilities.
 
 RDoc documentation is also available and the test directory has examples of usage.
 
+## In memory render and extraction
+
+```ruby
+# Assuming AWS::S3 is already authorized elsewhere
+bucket = AWS::S3.new.buckets['my-pdfs']
+
+pdf = PDFium::Document.from_memory bucket.objects['secrets.pdf'].read
+pdf.pages.each do | page |
+
+  # render the complete page as a PNG with the height locked to 1000 pixels
+  # The width will be calculated to maintain the proper aspect ratio
+  path = "secrets/page-#{page.number}.png"
+  bucket.objects[path].write page.as_image(height: 1000).data(:png)
+
+  # extract and save each embedded image as a PNG
+  page.images.each do | image |
+    path = "secrets/page-#{page.number}-image-#{image.index}.png"
+    bucket.objects[path].write image.data(:png)
+  end
+
+  # Extract text from page.  Will be encoded as UTF-16LE by default
+  path = "secrets/page-#{page.number}-text.txt"
+  bucket.objects[path].write page.text
+
+end
+```
+
 ## Open and saveing
 
 ```ruby
@@ -28,7 +55,6 @@ pdf.metadata
 Returns a hash with keys = :title, :author :subject, :keywords, :creator, :producer, :creation_date, :mod_date
 
 
-
 ## Bookmarks
 
 ```ruby

data/ext/pdfium_ext/bookmark.cc

@@ -200,15 +200,12 @@ bookmark_destination(VALUE self)
     return hash;
 }
 
-VALUE
+void
 define_bookmark_class(){
 
-#if RDOC_IS_STUPID_AND_CANNOT_PARSE_DOCUMENTATION
-    VALUE RB_PDFium = rb_define_module("PDFium");
-#endif
-    VALUE RB_PDFium = RB::PDFium();
+    VALUE PDFium = RB::PDFium();
 
-    VALUE RB_Bookmark = rb_define_class_under(RB_PDFium, "Bookmark",  rb_cObject);
+    VALUE RB_Bookmark = rb_define_class_under(PDFium, "Bookmark",  rb_cObject);
     rb_define_alloc_func(RB_Bookmark, bookmark_allocate);
 
     rb_define_private_method (RB_Bookmark, "initialize",   RUBY_METHOD_FUNC(bookmark_initialize),  1);
@@ -217,5 +214,4 @@ define_bookmark_class(){
     rb_define_method         (RB_Bookmark, "children",     RUBY_METHOD_FUNC(bookmark_children),    0);
     rb_define_method         (RB_Bookmark, "destination",  RUBY_METHOD_FUNC(bookmark_destination), 0);
 
-    return RB_Bookmark;
 }

data/ext/pdfium_ext/document.cc

@@ -10,14 +10,8 @@
 #include "buffer_file_write.hpp"
 
 /////////////////////////////////////////////////////////////////////////
-// The Document class                                                       //
+// The Document class                                                  //
 /////////////////////////////////////////////////////////////////////////
-/*
-    * Document-class:  PDFium::Document
-    *
-    * A Document represents a PDF file.
-    *
-*/
 
 
 // While you might think this would free the Document object it does not
@@ -74,7 +68,7 @@ document_initialize(int argc, VALUE *argv, VALUE self)
  *
  * Initializes a document from a binary string.
  *
- * See Image#data for an example of reading a PDF directly from Amazon S3
+ * See {PDFium::Image#data} for an example of reading a PDF directly from Amazon S3
  * and writing it's images completely in memory.
  */
 static VALUE
@@ -86,8 +80,8 @@ document_from_memory(VALUE klass, VALUE data){
 }
 
 /*
- * call-seq:
- *   page_count -> Fixnum
+ * @overload page_count
+ * page_count -> Fixnum
  *
  * Returns the number of pages on a Document
  */
@@ -98,7 +92,9 @@ document_page_count(VALUE self)
 }
 
 // Not documented in favor of the Document#pages[] access
-/* :nodoc: */
+/*
+  @private
+ */
 static VALUE
 document_page_at(VALUE self, VALUE rb_page_index)
 {
@@ -107,7 +103,8 @@ document_page_at(VALUE self, VALUE rb_page_index)
 
 /*
  * call-seq:
- *   pages -> PDFium::PageList
+ *   pages
+ * @return {PDFium::PageList}
  *
  * Returns a collection of all the pages on the document as a PDFium::PageList. Pages
  * are lazily loaded.
@@ -123,7 +120,7 @@ document_pages(VALUE self)
 
 // creates and yields a page.  Not documented since all access
 // should got through the Pageist interface via the Document#pages method
-/* :nodoc: */
+/* @private */
 static VALUE
 document_each_page(VALUE self)
 {
@@ -143,7 +140,9 @@ document_each_page(VALUE self)
 
 /*
  * call-seq:
- *   bookmarks -> Bookmarks
+ *   bookmarks
+ *
+ * @return {PDFium::BookmarkList}
  *
  * Retrieves the first Bookmark for a document
  */
@@ -160,13 +159,14 @@ document_bookmarks(VALUE self)
 
 
 
-
 /*
  * call-seq:
- *   save -> Document
+ *   save(file)
+ *
+ * @param file [String, Pathname] path to save the file to
+ * @return [Boolean] indicating success or failure
  *
- * Saves document to a PDF file.  This method isn't terribly useful since there aren't
- * (yet) methods to add content to pages.
+ * Retrieves the first Bookmark for a document
  */
 static VALUE
 document_save(VALUE self, VALUE _path)
@@ -244,13 +244,13 @@ document_metadata(int argc, VALUE *argv, VALUE self)
     return metadata;
 }
 
-VALUE
+void
 define_document_class()
 {
-    VALUE RB_PDFium = RB::PDFium();
+    VALUE PDFium = RB::PDFium();
 
     // The Document class definition and methods
-    VALUE RB_Document = rb_define_class_under(RB_PDFium, "Document",  rb_cObject);
+    VALUE RB_Document = rb_define_class_under(PDFium, "Document",  rb_cObject);
 
     rb_define_alloc_func(RB_Document, document_allocate);
 
@@ -264,5 +264,4 @@ define_document_class()
     rb_define_method         (RB_Document, "metadata",   RUBY_METHOD_FUNC(document_metadata),   -1);
     rb_define_method         (RB_Document, "bookmarks",  RUBY_METHOD_FUNC(document_bookmarks),   0);
     rb_define_method         (RB_Document, "save",       RUBY_METHOD_FUNC(document_save),        1);
-    return RB_Document;
 }

data/ext/pdfium_ext/extconf.rb

@@ -5,53 +5,36 @@ def existing(dirs)
   dirs.select{|dir| Dir.exist?(dir) }
 end
 
-LIB_DIRS=[]
-# if ENV['PDFIUM']
-#     LIB_DIRS    = [ "#{ENV['PDFIUM']}/out/Debug/lib.target" ]
-#     HEADER_DIRS = [
-#       "#{ENV['PDFIUM']}/fpdfsdk/include",
-#       "#{ENV['PDFIUM']}/core/include",
-#       "#{ENV['PDFIUM']}"
-#     ]
 
-# else
-#     LIB_DIRS = [
-#       "/usr/local/lib/pdfium",
-#       "/usr/lib/pdfium"
-#     ]
+if ENV['PDFIUM']
+    LIB_DIRS    = [ "#{ENV['PDFIUM']}/out/Debug/lib.target" ]
+    HEADER_DIRS = [
+      "#{ENV['PDFIUM']}/public",
+      "#{ENV['PDFIUM']}/core/include",
+      "#{ENV['PDFIUM']}"
+    ]
 
-#     HEADER_DIRS = [
-#       "/usr/include/pdfium",
-#       "/usr/local/include/pdfium",
-#       "/usr/local/include/pdfium/fpdfsdk/include",
-#       "/usr/local/include/pdfium/core/include"
-#     ]
-# end
-
-HEADER_DIRS=[
-    "/home/nas/pdfium/deb-package/pdfium/fpdfsdk/include",
-    "/home/nas/pdfium/deb-package/pdfium/core/include",
-    "/home/nas/pdfium/deb-package/pdfium"
-]
+else
+    LIB_DIRS = [
+        "/usr/local/lib/pdfium",
+        "/usr/lib/pdfium"
+    ]
+
+    HEADER_DIRS = [
+        "/usr/include/pdfium",
+        "/usr/include/pdfium/core/include",
+        "/usr/local/include/pdfium",
+        "/usr/local/include/pdfium/core/include"
+    ]
+end
 
 have_library('pthread')
 
-DEBUG = ENV['DEBUG'] == '1'
+DEBUG = ENV['DEBUG']
 
 $CPPFLAGS += " -Wall "
-$CPPFLAGS += " -g" #if DEBUG
+$CPPFLAGS += " -g" if DEBUG
 
-# The order that the libs are listed matters for Linux!
-# to debug missing symbols you can run:
-#    for l in `ls /usr/lib/pdfium/*.a`; do echo $l; nm $l | grep '<missing symbol>'; done
-# The listing with a "T" contains the symbol, the ones with a "U"
-# depend on it.  The "U" libs must come after the "T"
-# LIBS=%w{
-#   javascript bigint     freetype fpdfdoc     fpdftext        formfiller  icudata    icuuc
-#   icui18n    v8_libbase v8_base  v8_snapshot v8_libplatform  jsapi       pdfwindow  fxedit
-#   fxcrt      fxcodec    fpdfdoc  fdrm fxge   fpdfapi         freetype    pdfium
-#   pthread    freeimage
-# }
 LIBS=%w{pdfium freeimage}
 
 dir_config("libs", existing(HEADER_DIRS), existing(LIB_DIRS))

data/ext/pdfium_ext/image.cc

@@ -9,9 +9,9 @@
     * Document-class:  PDFium::Image
     *
     * A Image can represent either a Page that
-    * has been rendered to a Image via Page#as_image
+    * has been rendered to a Image via {PDFium::Page#as_image}
     *
-    * Or an embedded image on a Page, obtained via Page#images
+    * Or an embedded image on a {PDFium::Page}, obtained via {PDFium::Page#images}
 */
 
 
@@ -215,10 +215,14 @@ image_as_science(VALUE self){
 }
 
 /*
- * call-seq:
- *   save( file ) -> Boolean
- *
- * Save image to a file
+ call-seq:
+   save( file )
+
+ Save image to a file
+
+ @param file [String, Pathname] path to file to save image to
+ @return [Boolean] indicating success or failure
+
  */
 VALUE
 image_save(VALUE self, VALUE rb_file){
@@ -242,9 +246,10 @@ image_save(VALUE self, VALUE rb_file){
 
 /*
  call-seq:
-   data(:format) -> Binary String
+   data(:format)
 
- Returns the binary data for the image in the specified format.
+ @param format [symbol] any file extension recogized by FreeImage.
+ @return String containing binary data for the image in the specified format.
 
  Used in conjuction with Document.from_memory this can render be used to
  render a PDF's pages completely in memory.
@@ -301,16 +306,15 @@ image_data(VALUE self, VALUE rb_format)
     return ret;
 }
 
-VALUE
+void
 define_image_class(){
-    VALUE RB_PDFium = RB::PDFium();
+    VALUE PDFium = RB::PDFium();
+    VALUE RB_Image = rb_define_class_under(PDFium, "Image",  rb_cObject);
 
-
-    VALUE RB_Image = rb_define_class_under(RB_PDFium, "Image",  rb_cObject);
     rb_define_alloc_func(RB_Image, image_allocate);
     rb_define_private_method (RB_Image, "initialize",   RUBY_METHOD_FUNC(image_initialize),  -1);
 
-    /* Returns the bouding box of the image as a PDFium::BoundingBox */
+    /* Returns the bouding box of the image as a {PDFium::BoundingBox} */
     rb_define_attr( RB_Image, "bounds", 1, 0 );
 
     /* Returns the index of the image on the page.
@@ -328,5 +332,5 @@ define_image_class(){
     rb_define_method( RB_Image, "save", RUBY_METHOD_FUNC(image_save), 1);
     rb_define_method( RB_Image, "data", RUBY_METHOD_FUNC(image_data), 1);
     rb_define_method( RB_Image, "as_science", RUBY_METHOD_FUNC(image_as_science),0);
-    return RB_Image;
+
 }

data/ext/pdfium_ext/page.cc

@@ -22,8 +22,7 @@ static VALUE rb_sym_width;
 
 /*
     * Document-class:  PDFium::Page
-    *
-    * A Page on a PDF Document
+    * A Page on a PDFium::Document
 */
 static void
 page_gc_free(PageWrapper* page)
@@ -338,9 +337,10 @@ page_each_image(VALUE self)
     PageWrapper *pw;
     Data_Get_Struct(self, PageWrapper, pw);
 
-    auto count = pw->page()->CountObjects();
+    unsigned int count = pw->page()->CountObjects();
     int image_index=0;
-    for (int index=0; index < count; index++){
+
+    for (unsigned int index=0; index < count; index++){
         CPDF_PageObject *object = pw->page()->GetObjectByIndex(index);
         if ( PDFPAGE_IMAGE == object->m_Type ){
             VALUE args[2];
@@ -360,18 +360,18 @@ page_each_image(VALUE self)
 }
 
 
-VALUE
+
+void
 define_page_class()
 {
     rb_sym_width  = ID2SYM(rb_intern("width"));
     rb_sym_height = ID2SYM(rb_intern("height"));
 
-    VALUE RB_PDFium = RB::PDFium();
-
-    // The Page class definition and methods
-    VALUE RB_Page = rb_define_class_under(RB_PDFium, "Page", rb_cObject);
-    //rb_define_alloc_func     (RB_Page, page_allocate);
-    //rb_define_private_method (RB_Page, "initialize",   RUBY_METHOD_FUNC(page_initialize), -1);
+    VALUE PDFium = RB::PDFium();
+    /*
+     The Page class definition and methods
+     */
+    VALUE RB_Page = rb_define_class_under( PDFium, "Page", rb_cObject);
 
     rb_define_singleton_method(RB_Page, "new",    RUBY_METHOD_FUNC(page_new),    0);
     rb_define_singleton_method(RB_Page, "open",   RUBY_METHOD_FUNC(page_open),   2);
@@ -388,5 +388,5 @@ define_page_class()
 
     rb_define_method         (RB_Page, "each_image", RUBY_METHOD_FUNC(page_each_image), 0);
 
-    return RB_Page;
+
 }

data/ext/pdfium_ext/pdfium.h

@@ -3,20 +3,17 @@
 
 #include <stdlib.h>
 #include <inttypes.h>
-#include <fpdf_dataavail.h>
-#include <fpdf_ext.h>
-#include <fpdfformfill.h>
-#include <fpdftext.h>
-#include <fpdfview.h>
-#include <fpdfedit.h>
-#include <fpdfsave.h>
-#include <fpdfdoc.h>
 #include <iostream>
-#include <fpdfdoc/fpdf_doc.h>
 
-#include <fpdfapi/fpdf_render.h>
+#include <fpdf_doc.h>
+#include <fpdf_save.h>
+#include <fpdf_edit.h>
+#include <fpdf_text.h>
+#include <fpdfdoc/fpdf_doc.h>
+#include <fpdfapi/fpdf_page.h>
 #include <fpdfapi/fpdf_pageobj.h>
-#include <fpdfsdk/include/fsdk_rendercontext.h>
+#include <fpdftext/fpdf_text.h>
+
 #include <FreeImage.h>
 
 #include "page_wrapper.h"
@@ -35,10 +32,10 @@ extern "C" {
 #define DEBUG_MSG(str) do { } while ( false )
 #endif
 
-VALUE define_bookmark_class();
-VALUE define_document_class();
-VALUE define_page_class();
-VALUE define_image_class();
+void define_bookmark_class();
+void define_document_class();
+void define_page_class();
+void define_image_class();
 
 // a utility method to extract the reference to the FPDF_DOCUMENT from the Ruby/C++ wrapping
 

data/lib/pdfium/version.rb

@@ -1,4 +1,4 @@
 module PDFium
     # Gem version
-    VERSION = "0.0.1"
+    VERSION = "0.0.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdfium
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Nathan Stitt
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-31 00:00:00.000000000 Z
+date: 2015-06-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -119,6 +119,7 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".ruby-version"
+- ".yardopts"
 - Gemfile
 - Guardfile
 - LICENSE.txt