mupdf 0.3.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 025aace876d1fc5f6ba89c7e94fb7a618b645c5011d1eb7d3923252ca1643693
-  data.tar.gz: 9cc27d161818550e2b3290933652be4c1b8474f550f7c6f71a59eda5af4f02cc
+  metadata.gz: 75c0956dd50c089d4cea76952bdc5c4244a946c674d4e648edc71d749bd1faca
+  data.tar.gz: c5fe14cf7c06739d4e03480c894ab938c4e0fa68b897bdcf4b49e0f078f33bf5
 SHA512:
-  metadata.gz: baf0ad502de63e12d938481d8944a96091a74f85e5d42189bcac9b7b0afb5b262f133e70eae434ac3f129349105262ececeff6e3feadbc037f4be14fd7127502
-  data.tar.gz: 90a9bedd5984280f820b76bbbcab596bea290bdb79c6e699cf029898569cc006e23e7c26ea1877a95d8406a025e2dd70f2faec675f8aab0af2b143d9fa76352f
+  metadata.gz: 842db6317559209c6f2a6b0205adc8e2792c395be8fc61c0b5b23a6d750d86daf8a9642b656661efea26981cbbe6e8b64c83cd9448b470941bedc7c8011df04c
+  data.tar.gz: e3e79b6054b2f4f32947d62b64ca421d71efe1c949d544e99e0464503a22dde8472d4cb5da7e8cf9770d464dd7bd0f8e5b2a95d8351ab7c9347edd88405b32b9

data/Gemfile

@@ -11,4 +11,5 @@ gem 'rubocop'
 gem 'rubocop-rake'
 gem 'rubocop-rspec'
 gem 'simplecov'
+gem 'tempfile'
 gem 'yard'

data/README.md

@@ -12,11 +12,29 @@
 gem install mupdf
 ```
 
+_This project requires `mutool` be installed on your system. To verify ensure the following works:_
+
+```bash
+mutool
+```
+
+To install `mutool` on MacOS use:
+
+```bash
+brew install mupdf
+```
+
+To install `mutool` on Ubuntu use:
+
+```bash
+apt-get install mupdf
+```
+
 ## Usage
 
 ### Document
 
-A `MuPDF::Document` wraps for a file:
+A `MuPDF::Document` wraps a PDF file:
 
 ```ruby
 document = MuPDF::Document.new('./file.pdf')
@@ -24,9 +42,33 @@ document = MuPDF::Document.new('./file.pdf')
 
 #### Info
 
-The `info` command displays information about a document such as the number of pages:
+The `info` command displays information about the document such as the number of pages:
 
 ```ruby
 info = document.info
 info.pages # e.g. 2
 ```
+
+#### Pages
+
+The `pages` command finds sizing information about the pages within a document:
+
+```ruby
+pages = document.pages
+pages.count # e.g. 2
+pages.each do |page|
+  page.number # e.g. 1, 2, ...
+  page.width # 612
+  page.height # 792
+end
+```
+
+#### Draw
+
+The `draw` command is useful for converting a document between formats:
+
+```ruby
+document.pages.each do |page|
+  document.draw(page: page.number, format: "png", path: "./file-#{page.number}.png")
+end
+```

data/lib/mupdf/box.rb

@@ -0,0 +1,72 @@
+# frozen_string_literal: true
+
+module MuPDF
+  # A bounding box for a PDF (e.g. media / crop / bleed / trim).
+  class Box
+    REGEX = /l="(?<l>\d+)" b="(?<b>\d+)" r="(?<r>\d+)" t="(?<t>\d+)"/
+
+    # @!attribute l
+    #   @return [String] The left coordinate.
+    attr_reader :l
+
+    # @!attribute b
+    #   @return [String] The bottom coordinate.
+    attr_reader :b
+
+    # @!attribute r
+    #   @return [String] The right coordinate.
+    attr_reader :r
+
+    # @!attribute t
+    #   @return [String] The top coordinate.
+    attr_reader :t
+
+    # @!attribute kind
+    #   @return [Symbol] The kind of box.
+    attr_reader :kind
+
+    # @param text [String]
+    # @param kind [Symbol]
+    #
+    # @return [MuPDF::Box]
+    def self.parse(text, kind:)
+      match = text.match(REGEX)
+
+      new(
+        l: Integer(match[:l]),
+        b: Integer(match[:b]),
+        r: Integer(match[:r]),
+        t: Integer(match[:t]),
+        kind:
+      )
+    end
+
+    # @param l [Integer]
+    # @param b [Integer]
+    # @param r [Integer]
+    # @param t [Integer]
+    # @param kind [Symbol] optional
+    def initialize(l:, b:, r:, t:, kind: nil)
+      @l = l
+      @b = b
+      @r = r
+      @t = t
+      @kind = kind
+    end
+
+    # @return [String]
+    def inspect
+      "#<#{self.class.name} l=#{l} b=#{b} r=#{r} t=#{t} kind=#{kind}>"
+    end
+
+    # @return [Integer]
+    def width
+      @r - @l
+    end
+
+    # @return [Integer]
+    def height
+      @t - @b
+    end
+  end
+end

data/lib/mupdf/document.rb

@@ -8,6 +8,14 @@ module MuPDF
       @pathname = pathname
     end
 
+    # @return [String]
+    def inspect
+      "#<#{self.class.name} pathname=#{@pathname}>"
+    end
+
+    # @usage
+    #   document.info #=> #<MuPDF::Info ...>
+    #
     # @raise [MuPDF::CommandError]
     #
     # @return [MuPDF::Info]
@@ -17,5 +25,46 @@ module MuPDF
         MuPDF::Info.parse(result)
       end
     end
+
+    # @usage
+    #   pages = document.pages #=> [#<MuPDF::Page ...>, ...]
+    #   pages.each do |page|
+    #     puts page.number # e.g. 1, 2, 3, ...
+    #     puts page.width # e.g. 612
+    #     puts page.height # e.g. 792
+    #   end
+    #
+    # @raise [MuPDF::CommandError]
+    #
+    # @return [Array<MuPDF::Page>]
+    def pages
+      @pages ||= begin
+        result = MuPDF.mutool('pages', String(@pathname))
+        MuPDF::Page.parse(result)
+      end
+    end
+
+    # @usage
+    #   Tempfile.open(['mupdf', '.png']) do |tempfile|
+    #     document.draw(path: tempfile.path, page: 2, format: 'png')
+    #   end
+    #
+    # @param path [String] the path where the conversion is saved
+    # @param format [String] "png", "svg", "txt", etc
+    # @param page [Integer] the page
+    # @param resultion [Integer] optional (default: 72)
+    # @param width [Integer] optional
+    # @param height [Integer] optional
+    #
+    # @raise [MuPDF::CommandError]
+    def draw(path:, page:, format: 'png', width: nil, height: nil, resolution: nil)
+      args = ['draw', '-o', path, '-F', format, String(@pathname), String(page)]
+
+      args << '-w' << width if width
+      args << '-h' << height if height
+      args << '-r' << resolution if resolution
+
+      MuPDF.mutool(*args)
+    end
   end
 end

data/lib/mupdf/page.rb

@@ -0,0 +1,123 @@
+# frozen_string_literal: true
+
+module MuPDF
+  # A wrapper for a PDF page within a PDF document.
+  class Page
+    REGEX = %r{<page pagenum="(?<pagenum>\d+)">(?<content>.*?)</page>}m
+    MEDIA_BOX_REGEX = %r{<MediaBox (?<content>.*?) />}
+    CROP_BOX_REGEX = %r{<CropBox (?<content>.*?) />}
+    ART_BOX_REGEX = %r{<ArtBox (?<content>.*?) />}
+    BLEED_BOX_REGEX = %r{<BleedBox (?<content>.*?) />}
+    TRIM_BOX_REGEX = %r{<TrimBox (?<content>.*?) />}
+
+    # @param text [String]
+    #
+    # @return [Array<MuPDF::Page>]
+    def self.parse(text)
+      text.scan(REGEX).map do |number, content|
+        new(
+          media_box: parse_media_box(content),
+          crop_box: parse_crop_box(content),
+          art_box: parse_art_box(content),
+          bleed_box: parse_bleed_box(content),
+          trim_box: parse_trim_box(content),
+          number: Integer(number)
+        )
+      end
+    end
+
+    # @param text [String]
+    #
+    # @return [MuPDF::Box]
+    def self.parse_media_box(text)
+      match = MEDIA_BOX_REGEX.match(text)
+      MuPDF::Box.parse(match[:content], kind: :media)
+    end
+
+    # @param text [String]
+    #
+    # @return [MuPDF::Box]
+    def self.parse_crop_box(text)
+      match = CROP_BOX_REGEX.match(text)
+      MuPDF::Box.parse(match[:content], kind: :crop)
+    end
+
+    # @param text [String]
+    #
+    # @return [MuPDF::Box]
+    def self.parse_art_box(text)
+      match = ART_BOX_REGEX.match(text)
+      MuPDF::Box.parse(match[:content], kind: :art)
+    end
+
+    # @param text [String]
+    #
+    # @return [MuPDF::Box]
+    def self.parse_bleed_box(text)
+      match = BLEED_BOX_REGEX.match(text)
+      MuPDF::Box.parse(match[:content], kind: :bleed)
+    end
+
+    # @param text [String]
+    #
+    # @return [MuPDF::Box]
+    def self.parse_trim_box(text)
+      match = TRIM_BOX_REGEX.match(text)
+      MuPDF::Box.parse(match[:content], kind: :trim)
+    end
+
+    # @!attribute media_box
+    #   @return [MuPDFBox]
+    attr_accessor :media_box
+
+    # @!attribute crop_box
+    #   @return [MuPDFBox]
+    attr_accessor :crop_box
+
+    # @!attribute art_box
+    #   @return [MuPDFBox]
+    attr_accessor :art_box
+
+    # @!attribute bleed_box
+    #   @return [MuPDFBox]
+    attr_accessor :bleed_box
+
+    # @!attribute trim_box
+    #   @return [MuPDFBox]
+    attr_accessor :trim_box
+
+    # @!attribute pagenum
+    #   @return [Integer]
+    attr_accessor :pagenum
+
+    # @param media_box [MuPDF::Box]
+    # @param crop_box [MuPDF::Box]
+    # @param art_box [MuPDF::Box]
+    # @param bleed_box [MuPDF::Box]
+    # @param trim_box [MuPDF::Box]
+    # @param number [Integer]
+    def initialize(media_box:, crop_box:, art_box:, bleed_box:, trim_box:, number:)
+      @media_box = media_box
+      @crop_box = crop_box
+      @art_box = art_box
+      @bleed_box = bleed_box
+      @trim_box = trim_box
+      @number = number
+    end
+
+    # @return [String]
+    def inspect
+      "#<#{self.class.name} number=#{@number}>"
+    end
+
+    # @return [Integer]
+    def width
+      @media_box.width
+    end
+
+    # @return [Integer]
+    def height
+      @media_box.height
+    end
+  end
+end

data/lib/mupdf/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module MuPDF
-  VERSION = '0.3.0'
+  VERSION = '1.0.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: mupdf
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Kevin Sylvestre
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-01-02 00:00:00.000000000 Z
+date: 2025-01-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open3
@@ -50,9 +50,11 @@ files:
 - bin/console
 - bin/setup
 - lib/mupdf.rb
+- lib/mupdf/box.rb
 - lib/mupdf/command_error.rb
 - lib/mupdf/document.rb
 - lib/mupdf/info.rb
+- lib/mupdf/page.rb
 - lib/mupdf/version.rb
 homepage: https://github.com/ksylvest/mupdf
 licenses:
@@ -60,8 +62,8 @@ licenses:
 metadata:
   rubygems_mfa_required: 'true'
   homepage_uri: https://github.com/ksylvest/mupdf
-  source_code_uri: https://github.com/ksylvest/mupdf/tree/v0.3.0
-  changelog_uri: https://github.com/ksylvest/mupdf/releases/tag/v0.3.0
+  source_code_uri: https://github.com/ksylvest/mupdf/tree/v1.0.0
+  changelog_uri: https://github.com/ksylvest/mupdf/releases/tag/v1.0.0
   documentation_uri: https://mupdf.ksylvest.com/
 post_install_message: 
 rdoc_options: []