toc_extract 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8166372166f4ca2fc3242398b6c9ff620bdc0760260a882e6373fec870361a84
-  data.tar.gz: 8a10993154383702ed1629e8f20026a817f3115ed076c06cbe4e8ccce561fcbd
+  metadata.gz: 6b4ad0c8374da7bd65d180846d2cdc3753de5882414e2bd8c9938cf5c6576f69
+  data.tar.gz: 10576f74ffbe6849cd18de5448dcc4cbfd86c77b058b3aa854bdbfe4f0961597
 SHA512:
-  metadata.gz: dc2c0915f1c84cda13741dcc674c4878c1731e275c012293dcbc55dc366f50f27a80cda053c6ee00c8522017355651c625b6b81d477c90a84b54899aff64cad5
-  data.tar.gz: 647c126a09844ed72603180b6f2d9569bf83537240d5bdea89dbfdca06a2478dd39800b6a981502ddfaced54f6e662bfb0e6d434a4c97d7da1124e85e7a85655
+  metadata.gz: 6ac11b25e4d645093870437716cb1532e439fc0224e90d5312781a730081333cb7cc9e2221aa53c1938b81b647ac603a9a49d08cbceec7a7604a214a8474d7e4
+  data.tar.gz: 9786a77f1068b8489243c067ea5e95b77921c3689bdc28115768748e65515ff13cc38ded2bf6c3247d18a75bf3ad54bd4d62e9296d49cfca91a88cf2256073e0

data/lib/toc_extract/extractor.rb

@@ -11,6 +11,14 @@ class TocExtract
   require "pdf/reader"
   require "pdf/reader/find_text"
 
+  def self.extract(pdf_file, template, toc_start_page, toc_end_page)
+    lines = TocExtract.toc_lines(pdf_file, template, toc_start_page, toc_end_page)
+    sections = TocExtract.sections_from_toc_lines(lines, template)
+    TocExtract.fill_bounding_boxes(pdf_file, sections, toc_end_page)
+
+    sections
+  end
+
 
   def self.toc_lines(pdf_file, template, toc_start_page, toc_end_page)
     # To detect the lines, we assume that all the elements on a line have the same y value.
@@ -98,7 +106,7 @@ class TocExtract
           break
         end
       end
-      page = page.reverse.to_i
+      page = page.reverse.to_i - 1 # Since TOC pages are 1-based
 
       # title
       title = line[title_start..title_end-1].sub(/\.+$/, '')

data/lib/toc_extract/preview.rb

@@ -0,0 +1,54 @@
+class TocExtract
+  def self.preview(pdf_file, section, crop_width, crop_height)
+    require "rmagick"
+    require "pdf/reader"
+    require "pdf/reader/find_text"
+
+    result = "" 
+
+    PDF::Reader.open(pdf_file) do |reader|
+      page_num = section.page_number
+
+      target_page = reader.pages[page_num]
+      page_width = target_page.width
+      page_height = target_page.height
+
+      images = Magick::Image.read("#{pdf_file}[#{page_num}]") do |info|
+        info.density = 150
+      end
+
+      img = images.first
+      img_width = img.columns
+      img_height = img.rows
+
+      scale_x = img_width.to_f / page_width
+      scale_y = img_height.to_f / page_height
+
+      # In pdf, x,y are the bottom left coordinates, converting them to top left
+      # Convert pdf-reader coordinates to RMagick coordinates
+      # pdf-reader: origin at bottom-left, Y increases upward
+      # RMagick: origin at top-left, Y increases downward
+      # Add some padding as well
+      pdf_x = section.bounding_box["x"] - 30
+      pdf_y = section.bounding_box["endy"] + 10
+
+      img_x = (pdf_x * scale_x).round
+      img_y = ((page_height - pdf_y) * scale_y).round  # Flip Y coordinate
+      img_width_pixels = (crop_width * scale_x).round
+      img_height_pixels = (crop_height * scale_y).round
+
+      # Ensure coordinates are within image bounds
+      img_x = [ img_x, 0 ].max
+      img_y = [ img_y, 0 ].max
+      img_width_pixels = [ img_width_pixels, img_width ].min
+      img_height_pixels = [ img_height_pixels, img_height ].min
+
+      cropped_img = img.crop(img_x, img_y, img_width_pixels, img_height_pixels)
+
+      cropped_img.resize_to_fit!(crop_width, crop_height)
+      result = cropped_img.to_blob { |info| info.format = "PNG" }
+    end
+    
+    result
+  end
+end

data/lib/toc_extract.rb

@@ -6,3 +6,4 @@ class TocExtract
 end
 
 require_relative 'toc_extract/extractor'
+require_relative 'toc_extract/preview'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: toc_extract
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Arash Afshar
@@ -37,6 +37,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rmagick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '6.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '6.1'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -119,6 +133,7 @@ files:
 - README.md
 - lib/toc_extract.rb
 - lib/toc_extract/extractor.rb
+- lib/toc_extract/preview.rb
 homepage: https://github.com/Arash-Afshar/toc_extract
 licenses:
 - MIT