asciidoctor_cjk_breaks 0.0.1 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9c02afe8dd442f8c710ba0d7378e7725aac105a6f50531c380611d318860376e
-  data.tar.gz: d3ba448088b097772c1e0e04be5075ae89b3e2072d9ceb08a056f2a3f54fe777
+  metadata.gz: 2ab0bb16cfe28013986b1c52388a04745176560ea3504f49952a9d605395e7c5
+  data.tar.gz: bb8faf93ff3508affcc83873ea85ef1161dbfa9a77c0cd3bf5a6be3aa504337c
 SHA512:
-  metadata.gz: ad97861be354b68c41f5c640667c7ce54ece7be6686287cb73d54a0ae614ebb3acf67f2e8b6b1590101a6b471eb3a1489b9ef96a29d1d25f238502f18d3b0614
-  data.tar.gz: 3962921d6e1500c0b825e49bee236ae3cfd0edb828ca8b480694265116fdccfcc8871ce53ceb22021b5ee3018ac6b8ce3d050a808161d6ea587b37131deb1c90
+  metadata.gz: 0ac77115546662ea97a1c6a35013f3168861c1376863c69b22b5837ff5bb566a44c7cb7a0275ff84ae8fd926aa6ac5935931bfa7244517b4329306e753ce1648
+  data.tar.gz: 2c35b6d8a78928e5db7421a42f522d4c9ececf6cc69f307bd35fcd7d8df86a4085182d96d336b6e5dc9bbdf514e84d24bb873691e96d66f018e99ccc6e6d1303

data/README.adoc

@@ -15,7 +15,7 @@ This extension finds and removes newlines that cannot be converted to space, alg
 
 This is a Ruby port of https://github.com/markdown-it/markdown-it-cjk-breaks[markdown-it-cjk-breaks].
 
-Status: https://github.com/markdown-it/markdown-it-cjk-breaks/commit/15c7a4144e0e6f94fada671a6eb2c7b63e2358f0[15c7a41]
+Status: https://github.com/markdown-it/markdown-it-cjk-breaks/commit/26744838965b07ed5853031461600890b57238f7[2674483]
 
 == Install
 
@@ -23,8 +23,19 @@ Status: https://github.com/markdown-it/markdown-it-cjk-breaks/commit/15c7a4144e0
 
 == Usage
 
+In command line:
+
  $ asciidoctor -r asciidoctor_cjk_breaks example.adoc
 
+In Ruby:
+
+[source, ruby]
+--------------
+require 'asciidoctor_cjk_breaks'
+
+Asciidoctor.convert_file filepath
+--------------
+
 == Test
 
  $ ruby test/test_cjk_breaks.rb

data/lib/asciidoctor/cjk_breaks_treeprocessor.rb

@@ -3,57 +3,65 @@ require 'east_asian_width'
 
 class CjkBreaksTreeprocessor < Asciidoctor::Extensions::Treeprocessor
   def process(document)
-    return unless document.blocks?
-
-    remove_cjk_breaks document
+    process_interal document
     nil
   end
 
-  def remove_cjk_breaks(node)
-    node.blocks.each_with_index do |block, index|
-      if block.context == :paragraph
-        content_changed = false
-        # Processing after raw_source -> block.lines -> block.content in asciidoctor.
-        # It may be better to make this process while the process from raw_source -> block.lines
-        # whose code flow is:
-        # -> `Asciidoctor::Block.initialize`
-        # -> `Asciidoctor::Helpers.normalize_lines_from_string`.
-        lines = block.content.lines
-        lines.each_with_index do |line, line_index|
-          last_char_idx = line.rindex(/[^\r|\n]/)
-          last_char = line[last_char_idx]
-          next_line = lines[line_index + 1]
-          next_char = next_line[0] if next_line
+  def process_interal(block)
+    case block.context
+    when :paragraph
+      remove_cjk_breaks block
+    when :dlist
+      block
+    when :table
+      block
+    else
+      block.blocks.map! do |b|
+        process_interal b
+      end
+      block
+    end
+  end
 
-          next unless last_char && next_char
+  def remove_cjk_breaks(block)
+    content_changed = false
+    # NOTE: use block.lines instead of block.content to avoid issues of auto-generated content e.g. footnotes.
+    # see source code: https://github.com/asciidoctor/asciidoctor/blob/v2.0.23/lib/asciidoctor/block.rb#L98-L129
+    lines = block.lines
+    lines.each_with_index do |line, line_index|
+      last_char_idx = line.rindex(/[^\r|\n]/)
+      last_char = line[last_char_idx]
+      next_line = lines[line_index + 1]
+      next_char = next_line[0] if next_line
 
-          remove_break = false
+      next unless last_char && next_char
 
-          if last_char == "\u200b" || next_char == "\u200b"
-            # remove newline if it's adjacent to ZWSP
-            remove_break = true
-          elsif EastAsianWidth.east_asian_width(last_char).match?(/^[FWH]$/) &&
-                EastAsianWidth.east_asian_width(next_char).match?(/^[FWH]$/)
-            # remove newline if both characters are fullwidth (F), wide (W) or
-            # halfwidth (H), but not Hangul
-            remove_break = true if !hangul?(last_char) && !hangul?(next_char)
-          end
+      remove_break = false
 
-          if remove_break
-            lines[line_index] = line.chomp
-            content_changed = true
-          end
-        end
+      if last_char == "\u200b" || next_char == "\u200b"
+        # remove newline if it's adjacent to ZWSP
+        remove_break = true
+      elsif EastAsianWidth.east_asian_width(last_char).match?(/^[FWH]$/) &&
+            EastAsianWidth.east_asian_width(next_char).match?(/^[FWH]$/)
+        # remove newline if both characters are fullwidth (F), wide (W) or
+        # halfwidth (H), but not Hangul
+        remove_break = true if !hangul?(last_char) && !hangul?(next_char)
+      end
 
-        if content_changed
-          node.blocks[index] = create_paragraph block.document, lines.join(''), block.attributes
-        end
-      else
-        remove_cjk_breaks block
+      if remove_break
+        lines[line_index] = line.chomp
+        content_changed = true
       end
     end
+
+    if content_changed
+      create_paragraph block.document, lines.join(''), block.attributes
+    else
+      block
+    end
   end
 
+
   REGEXP_HANGUL_CHARS = /
     [
     \u1100-\u11FF

data/test/fixtures/cjk_breaks.txt

@@ -70,3 +70,12 @@ foo🈀
 .
 <p>foo🈀🈀foo</p>
 .
+
+Should process EOL correctly
+.
+image:image.png[img]
+text
+.
+<p><img src="image.png" alt="img">
+text</p>
+.

data/test/fixtures/dlist.txt

@@ -0,0 +1,14 @@
+hello::
+world
+goodbye::
+cruel world1
+
+***
+
+Dairy::
+* Milk
+* Eggs
+Bakery::
+* Bread
+Produce::
+* Bananas

data/test/fixtures/footnote.txt

@@ -0,0 +1,8 @@
+wordfootnote:[nota bene a].
+word{empty}footnote:[nota bene b].
+wordfootnote:[nota bene again].
+
+See <<heading>>.
+
+[[heading,Heading]]
+== Headingfootnote:[This is a heading with a footnote]

data/test/fixtures/table.txt

@@ -0,0 +1,20 @@
+|===
+
+| Cell in column 1, row 1 | Cell in column 2, row 1
+
+| Cell in column 1, row 2 | Cell in column 2, row 2
+
+| Cell in column 1, row 3 | Cell in column 2, row 3
+
+|===
+
+***
+
+[cols="3*"]
+|===
+|Cell in column 1, row 1 |Cell in column 2, row 1
+|Cell in column 3, row 1
+
+|Cell in column 1, row 2
+|Cell in column 2, row 2 |Cell in column 3, row 2
+|===

data/test/fixtures/tengwanggexu-wangbo.txt

@@ -1,4 +1,5 @@
-滕王阁序 --- 王勃
+= 滕王阁序
+王勃
 
 豫章故郡，洪都新府。
 星分翼轸，地接衡庐。

data/test/test_cjk_breaks.rb

@@ -2,3 +2,8 @@ require_relative '../lib/asciidoctor_cjk_breaks'
 
 Asciidoctor.convert_file 'test/fixtures/cjk_breaks.txt'
 Asciidoctor.convert_file 'test/fixtures/tengwanggexu-wangbo.txt'
+
+Asciidoctor.convert_file 'test/fixtures/dlist.txt'
+Asciidoctor.convert_file 'test/fixtures/table.txt'
+
+Asciidoctor.convert_file 'test/fixtures/footnote.txt'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: asciidoctor_cjk_breaks
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.3
 platform: ruby
 authors:
 - Kaizhao Zhang
-autorequire: 
+- Kefu Chai
 bindir: bin
 cert_chain: []
-date: 2018-11-09 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: asciidoctor
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.5'
+        version: '2'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.5'
+        version: '2'
 - !ruby/object:Gem::Dependency
   name: east_asian_width
   requirement: !ruby/object:Gem::Requirement
@@ -40,7 +40,9 @@ dependencies:
         version: '0'
 description: An extension for Asciidoctor that suppresses line breaks between east
   asian characters.
-email: zhangkaizhao@gmail.com
+email:
+- zhangkaizhao@gmail.com
+- tchaikov@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -49,13 +51,15 @@ files:
 - lib/asciidoctor/cjk_breaks_treeprocessor.rb
 - lib/asciidoctor_cjk_breaks.rb
 - test/fixtures/cjk_breaks.txt
+- test/fixtures/dlist.txt
+- test/fixtures/footnote.txt
+- test/fixtures/table.txt
 - test/fixtures/tengwanggexu-wangbo.txt
 - test/test_cjk_breaks.rb
 homepage: https://github.com/zhangkaizhao/asciidoctor_cjk_breaks
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -70,9 +74,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
-signing_key: 
+rubygems_version: 3.6.7
 specification_version: 4
 summary: Suppress line breaks between east asian characters
 test_files: []