toc_extract 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 8166372166f4ca2fc3242398b6c9ff620bdc0760260a882e6373fec870361a84
+  data.tar.gz: 8a10993154383702ed1629e8f20026a817f3115ed076c06cbe4e8ccce561fcbd
+SHA512:
+  metadata.gz: dc2c0915f1c84cda13741dcc674c4878c1731e275c012293dcbc55dc366f50f27a80cda053c6ee00c8522017355651c625b6b81d477c90a84b54899aff64cad5
+  data.tar.gz: 647c126a09844ed72603180b6f2d9569bf83537240d5bdea89dbfdca06a2478dd39800b6a981502ddfaced54f6e662bfb0e6d434a4c97d7da1124e85e7a85655

data/LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 TOCExtract Contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,5 @@
+# TocExtract: Extracts Table of Content from a PDF
+
+This is implemented for the specific case of the pdf in https://github.com/coinbase/cb-mpc/tree/master/docs.
+To run the tests, download https://github.com/coinbase/cb-mpc/blob/master/docs/spec/zk-proofs-spec.pdf at 3e54547 to the root directory.
+

data/lib/toc_extract/extractor.rb

@@ -0,0 +1,144 @@
+class Section
+  attr_accessor :id, :title, :page_number, :bounding_box
+  def initialize(id, title, page_number)
+    @id = id
+    @title = title
+    @page_number = page_number
+  end
+end
+
+class TocExtract
+  require "pdf/reader"
+  require "pdf/reader/find_text"
+
+
+  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.
+    # If this assumption changes in the future, we can instead list all the deltas between
+    # y values and compute breaking points where a noticeable jumpt in delta occures.
+
+    # template is a placeholder for future extensions. At the moment, always assume that
+    # each line starts with a section number, followed by section title and optionally
+    # some dots and ends with a page number. Morever, we assume that pages use arabic
+    # numbering as opposed to roman numerals.
+
+
+    lines = []
+    max_delta = 0
+    line = ""
+    last_y = 0
+    PDF::Reader.open(pdf_file) do |reader|
+      reader.pages.each_with_index do |page, page_num|
+        next if page_num < toc_start_page
+        break if page_num > toc_end_page
+        page.extend(PDF::Reader::FindText)
+        runs = page.runs(merge: false)
+        runs.each do |run|
+          y = run.y
+          last_y = y if last_y == 0
+          delta = (last_y - y).abs
+          if delta > max_delta
+            lines << line
+            line = run.text
+            last_y = y
+          else
+            line += run.text
+          end
+        end
+      end
+    end
+
+    # Merge lines based on the template. Currently, hard-coded as <NUMBER><TEXT>[...]<NUMBER>
+    # Also romeve the lines that contain page numbers. This should also be part of the template, assuming arabic numbering
+    real_lines = []
+    for line in lines
+      if line[0].match?(/[\d]/)
+        next if line.scan(/\D/).empty?
+        real_lines << line
+      else
+        # we could be unlucky and get a line that happens to have number in the its text portion
+        # and the line breaks at that exact moment. Ignoring for now.
+        if real_lines.length == 0
+          next # this is the toc header
+        else
+          real_lines[-1] += line
+        end
+      end
+    end
+
+    real_lines
+  end
+
+  def self.sections_from_toc_lines(lines, template)
+    # Same as before, the template is important, but is hard-coded as <NUMBER><TEXT>[...]<NUMBER>
+    sections = []
+    for line in lines
+      section_id = ""
+      page = ""
+
+      title_start = 0
+      title_end = line.length
+
+      # Section id
+      line.each_char do |c|
+        if c.match?(/[\d\.]/)
+          section_id += c
+          title_start += 1
+        else
+          break
+        end
+      end
+
+      # Page number
+      line.reverse.each_char do |c|
+        if c.match?(/[\d]/)
+          page += c
+          title_end -= 1
+        else
+          break
+        end
+      end
+      page = page.reverse.to_i
+
+      # title
+      title = line[title_start..title_end-1].sub(/\.+$/, '')
+      sections << Section.new(section_id, title, page)
+    end
+
+  sections
+  end
+
+  def self.fill_bounding_boxes(pdf_file, sections, toc_end_page)
+    i = 0
+    bboxes = {}
+    content_parts = []
+    PDF::Reader.open(pdf_file) do |reader|
+      reader.pages.each_with_index do |page, page_num|
+        next if page_num <= toc_end_page
+        page.extend(PDF::Reader::FindText)
+        runs = page.runs(merge: false)
+        runs.each do |run|
+          content_parts << run.text
+          bboxes[i] = {
+            "x" => run.x,
+            "y" => run.y,
+            "width" => run.width,
+            "endx" => run.endx,
+            "endy" => run.endy,
+            "page" => page_num
+          }
+          i += run.text.length
+        end
+      end
+    end
+    content = content_parts.join
+
+    # For each section, search in the content and find its position,
+    # look it up in the bounding box and store it
+    for section in sections
+      pos = content.index(section.title)
+      # puts "not found #{pos} for #{section.title}" if bboxes.key?(pos)
+      section.bounding_box = bboxes[pos]
+    end
+  end
+end

data/lib/toc_extract.rb

@@ -0,0 +1,8 @@
+class TocExtract
+  def self.hi(language = "english")
+    translator = Translator.new(language)
+    translator.hi
+  end
+end
+
+require_relative 'toc_extract/extractor'

metadata

@@ -0,0 +1,145 @@
+--- !ruby/object:Gem::Specification
+name: toc_extract
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Arash Afshar
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.15'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.15'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader-find_text
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.21'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.21'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+description: A Ruby gem for extracting and parsing table of contents from PDF documents
+  with bounding box information
+email:
+- arash.afshar.edu@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE.txt
+- README.md
+- lib/toc_extract.rb
+- lib/toc_extract/extractor.rb
+homepage: https://github.com/Arash-Afshar/toc_extract
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  source_code_uri: https://github.com/Arash-Afshar/toc_extract
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.9
+specification_version: 4
+summary: Extract table of contents from PDF files
+test_files: []