解析 markdown 缩进代码块

Question

我正在尝试使用用 Parslet 编写的语法来解析 Markdown。但是，我无法通过缩进代码块，因为到目前为止我尝试的所有内容都陷入了递归。它们看起来像这样：

    This is a indented code block.
    Second line.

    Code block continues after blank line.

    There can be any number of chunks, 
    separated by not more than one blank line.

为了解决这个问题，我写了一个最小的例子，用 a 替换行（包括 \n），用空格替换空行（\n\n），例如：a aaa aa.

# recurring_group_parser.rb

require 'parslet'
require 'rspec'
require 'parslet/rig/rspec'

class RecurringGroupParser < Parslet::Parser
  root(:block)

  rule :block do
    chunk.repeat(1,3)
  end

  rule :chunk do
    str('a').repeat(1,3) >> space
  end

  rule :space do
    str(' ') | chunk.absent?
  end
end

describe RecurringGroupParser do
  it 'should parse a' do
    is_expected.to parse "a"
  end

  it 'should parse aa' do
    is_expected.to parse "aa"
  end

  it 'should parse aaa' do
    is_expected.to parse "aaa"
  end

  it 'should parse a a' do
    is_expected.to parse "a a"
  end

  it 'should parse aa a' do
    is_expected.to parse "aa a"
  end

  it 'should parse aaa a' do
    is_expected.to parse "aaa a"
  end

  it 'should parse a aa' do
    is_expected.to parse "a aa"
  end

  it 'should parse a aaa' do
    is_expected.to parse "a aaa"
  end

  it 'should parse aa a' do
    is_expected.to parse "aa a"
  end

  it 'should parse aa aa' do
    is_expected.to parse "aa aa"
  end

  it 'should parse aa aaa' do
    is_expected.to parse "aa aaa"
  end

  it 'should parse aaa aa' do
    is_expected.to parse "aaa aa"
  end

  it 'should parse aaa aaa' do
    is_expected.to parse "aaa aaa"
  end

  it 'should parse a a a' do
    is_expected.to parse "a a a"
  end

  it 'should parse aa a a' do
    is_expected.to parse "aa a a"
  end

  it 'should parse aaa a a' do
    is_expected.to parse "aaa a a"
  end

  it 'should parse a aa a' do
    is_expected.to parse "a aa a"
  end

  it 'should parse aa aa a' do
    is_expected.to parse "aa aa a"
  end

  it 'should parse aaa aa a' do
    is_expected.to parse "aaa aa a"
  end

  it 'should parse a aaa a' do
    is_expected.to parse "a aaa a"
  end

  it 'should parse aa aaa a' do
    is_expected.to parse "aa aaa a"
  end

  it 'should parse aaa aaa a' do
    is_expected.to parse "aaa aaa a"
  end

  it 'should parse a a aa' do
    is_expected.to parse "a a aa"
  end

  it 'should parse aa a aa' do
    is_expected.to parse "aa a aa"
  end

  it 'should parse aaa a aa' do
    is_expected.to parse "aaa a aa"
  end

  it 'should parse a aa aa' do
    is_expected.to parse "a aa aa"
  end

  it 'should parse aa aa aa' do
    is_expected.to parse "aa aa aa"
  end

  it 'should parse aaa aa aa' do
    is_expected.to parse "aaa aa aa"
  end

  it 'should parse a aaa aa' do
    is_expected.to parse "a aaa aa"
  end

  it 'should parse aa aaa aa' do
    is_expected.to parse "aa aaa aa"
  end

  it 'should parse aaa aaa aa' do
    is_expected.to parse "aaa aaa aa"
  end

  it 'should parse a a aaa' do
    is_expected.to parse "a a aaa"
  end

  it 'should parse aa a aaa' do
    is_expected.to parse "aa a aaa"
  end

  it 'should parse aaa a aaa' do
    is_expected.to parse "aaa a aaa"
  end

  it 'should parse a aa aaa' do
    is_expected.to parse "a aa aaa"
  end

  it 'should parse aa aa aaa' do
    is_expected.to parse "aa aa aaa"
  end

  it 'should parse aaa aa aaa' do
    is_expected.to parse "aaa aa aaa"
  end

  it 'should parse a aaa aaa' do
    is_expected.to parse "a aaa aaa"
  end

  it 'should parse aa aaa aaa' do
    is_expected.to parse "aa aaa aaa"
  end

  it 'should parse aaa aaa aaa' do
    is_expected.to parse "aaa aaa aaa"
  end
end

运行 rspec recurring_group_parser.rb 工作正常。只有当我把换行符放回去时，它才会停止：

# recurring_group_parser.rb

require 'parslet'
require 'rspec'
require 'parslet/rig/rspec'

class RecurringGroupParser < Parslet::Parser
  root(:block)

  rule :block do
    chunk.repeat(1,3)
  end

  rule :chunk do
    line.repeat(1,3) >> blank_line
  end

  rule :line do
    str('a') >> newline
  end

  rule :blank_line do
    newline.repeat(2) | chunk.absent?
  end

  rule :newline do
    str("\n") | any.absent?
  end
end

describe RecurringGroupParser do
  it 'should parse a' do
    is_expected.to parse "a"
  end

  it 'should parse aa' do
    is_expected.to parse "a\na"
  end

  it 'should parse aaa' do
    is_expected.to parse "a\na\na"
  end

  it 'should parse a a' do
    is_expected.to parse "a\n\na"
  end

  it 'should parse aa a' do
    is_expected.to parse "a\na\n\na"
  end

  it 'should parse aaa a' do
    is_expected.to parse "a\naa\n\na"
  end

  it 'should parse a aa' do
    is_expected.to parse "a\n\na\na"
  end

  it 'should parse a aaa' do
    is_expected.to parse "a\n\na\na\na"
  end

  it 'should parse aa a' do
    is_expected.to parse "a\na\n\na"
  end

  it 'should parse aa aa' do
    is_expected.to parse "a\na\n\na\na"
  end

  it 'should parse aa aaa' do
    is_expected.to parse "a\na\n\na\na\na"
  end

  it 'should parse aaa aa' do
    is_expected.to parse "a\naa\n\na\na"
  end

  it 'should parse aaa aaa' do
    is_expected.to parse "a\naa\n\na\na\na"
  end

  it 'should parse a a a' do
    is_expected.to parse "a\n\na\n\na"
  end

  it 'should parse aa a a' do
    is_expected.to parse "a\na\n\na\n\na"
  end

  it 'should parse aaa a a' do
    is_expected.to parse "a\naa\n\na\n\na"
  end

  it 'should parse a aa a' do
    is_expected.to parse "a\n\na\na\n\na"
  end

  it 'should parse aa aa a' do
    is_expected.to parse "a\na\n\na\na\n\na"
  end

  it 'should parse aaa aa a' do
    is_expected.to parse "a\naa\n\na\na\n\na"
  end

  it 'should parse a aaa a' do
    is_expected.to parse "a\n\na\naa\n\na"
  end

  it 'should parse aa aaa a' do
    is_expected.to parse "a\na\n\na\naa\n\na"
  end

  it 'should parse aaa aaa a' do
    is_expected.to parse "a\naa\n\na\naa\n\na"
  end

  it 'should parse a a aa' do
    is_expected.to parse "a\n\na\n\na\na"
  end

  it 'should parse aa a aa' do
    is_expected.to parse "a\na\n\na\n\na\na"
  end

  it 'should parse aaa a aa' do
    is_expected.to parse "a\naa\n\na\n\na\na"
  end

  it 'should parse a aa aa' do
    is_expected.to parse "a\n\na\na\n\na\na"
  end

  it 'should parse aa aa aa' do
    is_expected.to parse "a\na\n\na\na\n\na\na"
  end

  it 'should parse aaa aa aa' do
    is_expected.to parse "a\naa\n\na\na\n\na\na"
  end

  it 'should parse a aaa aa' do
    is_expected.to parse "a\n\na\naa\n\na\na"
  end

  it 'should parse aa aaa aa' do
    is_expected.to parse "a\na\n\na\naa\n\na\na"
  end

  it 'should parse aaa aaa aa' do
    is_expected.to parse "a\naa\n\na\naa\n\na\na"
  end

  it 'should parse a a aaa' do
    is_expected.to parse "a\n\na\n\na\na\na"
  end

  it 'should parse aa a aaa' do
    is_expected.to parse "a\na\n\na\n\na\na\na"
  end

  it 'should parse aaa a aaa' do
    is_expected.to parse "a\naa\n\na\n\na\na\na"
  end

  it 'should parse a aa aaa' do
    is_expected.to parse "a\n\na\na\n\na\na\na"
  end

  it 'should parse aa aa aaa' do
    is_expected.to parse "a\na\n\na\na\n\na\na\na"
  end

  it 'should parse aaa aa aaa' do
    is_expected.to parse "a\naa\n\na\na\n\na\na\na"
  end

  it 'should parse a aaa aaa' do
    is_expected.to parse "a\n\na\naa\n\na\na\na"
  end

  it 'should parse aa aaa aaa' do
    is_expected.to parse "a\na\n\na\naa\n\na\na\na"
  end

  it 'should parse aaa aaa aaa' do
    is_expected.to parse "a\naa\n\na\naa\n\na\na\na"
  end
end

为了简化这一点，行只能由一个 a 组成并且没有缩进，但以后可以很容易地更改并且与无法完成解析无关。我也很确定 rule :blank_line 中的 chunk.absent? 和 rule :newline 中的 any.absent? 之间存在冲突，但我不知道如何解决这个问题并提供打破递归的标准.需要任何帮助！

Answer 1

在这种情况下，换行符可以是eof。在这种情况下换行。 repeat(2) 重复匹配eof。你想要"repeat(2,2)"。您可以使这些错误很容易找到 :)...只需使用我的叉子。

您可以使用 my fork of parslet 检测其循环方式。它捕获循环并告诉您发生了什么。它比通常的 parslet 慢，所以切换回来进行生产解析。

使用这个 Gemfile：

source "https://rubygems.org"

gem "parslet" , :git => "https://github.com/NigelThorne/parslet.git"
gem 'rspec'

你得到这些结果：

 9:23:40.20 > bundle exec rspec parser.rb
FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF

Failures:

  1) RecurringGroupParser should parse a
     Failure/Error: is_expected.to parse "a"
     RuntimeError:
       Grammar contains an infinite loop applying 'NEWLINE{2, }' at char position 1
       ...a<-- here
     # ./parser.rb:33:in `block (2 levels) in <top (required)>'

  2) RecurringGroupParser should parse aa
     Failure/Error: is_expected.to parse "a\na"
     RuntimeError:
       Grammar contains an infinite loop applying 'NEWLINE{2, }' at char position 3
       ...a
       a<-- here
     # ./parser.rb:37:in `block (2 levels) in <top (required)>'

  3) RecurringGroupParser should parse aaa
     Failure/Error: is_expected.to parse "a\na\na"
     RuntimeError:
       Grammar contains an infinite loop applying 'NEWLINE{2, }' at char position 5
       ...a
       a
       a<-- here
     # ./parser.rb:41:in `block (2 levels) in <top (required)>'

  4) RecurringGroupParser should parse a a
     Failure/Error: is_expected.to parse "a\n\na"
       expected BLOCK to be able to parse "a\n\na"
     # ./parser.rb:45:in `block (2 levels) in <top (required)>'

  5) RecurringGroupParser should parse aa a
     Failure/Error: is_expected.to parse "a\na\n\na"
       expected BLOCK to be able to parse "a\na\n\na"
     # ./parser.rb:49:in `block (2 levels) in <top (required)>'

  6) RecurringGroupParser should parse aaa a
     Failure/Error: is_expected.to parse "a\naa\n\na"
       expected BLOCK to be able to parse "a\naa\n\na"
     # ./parser.rb:53:in `block (2 levels) in <top (required)>'

  7) RecurringGroupParser should parse a aa
     Failure/Error: is_expected.to parse "a\n\na\na"
       expected BLOCK to be able to parse "a\n\na\na"
     # ./parser.rb:57:in `block (2 levels) in <top (required)>'

  8) RecurringGroupParser should parse a aaa
     Failure/Error: is_expected.to parse "a\n\na\na\na"
       expected BLOCK to be able to parse "a\n\na\na\na"
     # ./parser.rb:61:in `block (2 levels) in <top (required)>'

  9) RecurringGroupParser should parse aa a
     Failure/Error: is_expected.to parse "a\na\n\na"
       expected BLOCK to be able to parse "a\na\n\na"
     # ./parser.rb:65:in `block (2 levels) in <top (required)>'

  10) RecurringGroupParser should parse aa aa
     Failure/Error: is_expected.to parse "a\na\n\na\na"
       expected BLOCK to be able to parse "a\na\n\na\na"
     # ./parser.rb:69:in `block (2 levels) in <top (required)>'

  11) RecurringGroupParser should parse aa aaa
     Failure/Error: is_expected.to parse "a\na\n\na\na\na"
       expected BLOCK to be able to parse "a\na\n\na\na\na"
     # ./parser.rb:73:in `block (2 levels) in <top (required)>'

  12) RecurringGroupParser should parse aaa aa
     Failure/Error: is_expected.to parse "a\naa\n\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\na"
     # ./parser.rb:77:in `block (2 levels) in <top (required)>'

  13) RecurringGroupParser should parse aaa aaa
     Failure/Error: is_expected.to parse "a\naa\n\na\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\na\na"
     # ./parser.rb:81:in `block (2 levels) in <top (required)>'

  14) RecurringGroupParser should parse a a a
     Failure/Error: is_expected.to parse "a\n\na\n\na"
       expected BLOCK to be able to parse "a\n\na\n\na"
     # ./parser.rb:85:in `block (2 levels) in <top (required)>'

  15) RecurringGroupParser should parse aa a a
     Failure/Error: is_expected.to parse "a\na\n\na\n\na"
       expected BLOCK to be able to parse "a\na\n\na\n\na"
     # ./parser.rb:89:in `block (2 levels) in <top (required)>'

  16) RecurringGroupParser should parse aaa a a
     Failure/Error: is_expected.to parse "a\naa\n\na\n\na"
       expected BLOCK to be able to parse "a\naa\n\na\n\na"
     # ./parser.rb:93:in `block (2 levels) in <top (required)>'

  17) RecurringGroupParser should parse a aa a
     Failure/Error: is_expected.to parse "a\n\na\na\n\na"
       expected BLOCK to be able to parse "a\n\na\na\n\na"
     # ./parser.rb:97:in `block (2 levels) in <top (required)>'

  18) RecurringGroupParser should parse aa aa a
     Failure/Error: is_expected.to parse "a\na\n\na\na\n\na"
       expected BLOCK to be able to parse "a\na\n\na\na\n\na"
     # ./parser.rb:101:in `block (2 levels) in <top (required)>'

  19) RecurringGroupParser should parse aaa aa a
     Failure/Error: is_expected.to parse "a\naa\n\na\na\n\na"
       expected BLOCK to be able to parse "a\naa\n\na\na\n\na"
     # ./parser.rb:105:in `block (2 levels) in <top (required)>'

  20) RecurringGroupParser should parse a aaa a
     Failure/Error: is_expected.to parse "a\n\na\naa\n\na"
       expected BLOCK to be able to parse "a\n\na\naa\n\na"
     # ./parser.rb:109:in `block (2 levels) in <top (required)>'

  21) RecurringGroupParser should parse aa aaa a
     Failure/Error: is_expected.to parse "a\na\n\na\naa\n\na"
       expected BLOCK to be able to parse "a\na\n\na\naa\n\na"
     # ./parser.rb:113:in `block (2 levels) in <top (required)>'

  22) RecurringGroupParser should parse aaa aaa a
     Failure/Error: is_expected.to parse "a\naa\n\na\naa\n\na"
       expected BLOCK to be able to parse "a\naa\n\na\naa\n\na"
     # ./parser.rb:117:in `block (2 levels) in <top (required)>'

  23) RecurringGroupParser should parse a a aa
     Failure/Error: is_expected.to parse "a\n\na\n\na\na"
       expected BLOCK to be able to parse "a\n\na\n\na\na"
     # ./parser.rb:121:in `block (2 levels) in <top (required)>'

  24) RecurringGroupParser should parse aa a aa
     Failure/Error: is_expected.to parse "a\na\n\na\n\na\na"
       expected BLOCK to be able to parse "a\na\n\na\n\na\na"
     # ./parser.rb:125:in `block (2 levels) in <top (required)>'

  25) RecurringGroupParser should parse aaa a aa
     Failure/Error: is_expected.to parse "a\naa\n\na\n\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\n\na\na"
     # ./parser.rb:129:in `block (2 levels) in <top (required)>'

  26) RecurringGroupParser should parse a aa aa
     Failure/Error: is_expected.to parse "a\n\na\na\n\na\na"
       expected BLOCK to be able to parse "a\n\na\na\n\na\na"
     # ./parser.rb:133:in `block (2 levels) in <top (required)>'

  27) RecurringGroupParser should parse aa aa aa
     Failure/Error: is_expected.to parse "a\na\n\na\na\n\na\na"
       expected BLOCK to be able to parse "a\na\n\na\na\n\na\na"
     # ./parser.rb:137:in `block (2 levels) in <top (required)>'

  28) RecurringGroupParser should parse aaa aa aa
     Failure/Error: is_expected.to parse "a\naa\n\na\na\n\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\na\n\na\na"
     # ./parser.rb:141:in `block (2 levels) in <top (required)>'

  29) RecurringGroupParser should parse a aaa aa
     Failure/Error: is_expected.to parse "a\n\na\naa\n\na\na"
       expected BLOCK to be able to parse "a\n\na\naa\n\na\na"
     # ./parser.rb:145:in `block (2 levels) in <top (required)>'

  30) RecurringGroupParser should parse aa aaa aa
     Failure/Error: is_expected.to parse "a\na\n\na\naa\n\na\na"
       expected BLOCK to be able to parse "a\na\n\na\naa\n\na\na"
     # ./parser.rb:149:in `block (2 levels) in <top (required)>'

  31) RecurringGroupParser should parse aaa aaa aa
     Failure/Error: is_expected.to parse "a\naa\n\na\naa\n\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\naa\n\na\na"
     # ./parser.rb:153:in `block (2 levels) in <top (required)>'

  32) RecurringGroupParser should parse a a aaa
     Failure/Error: is_expected.to parse "a\n\na\n\na\na\na"
       expected BLOCK to be able to parse "a\n\na\n\na\na\na"
     # ./parser.rb:157:in `block (2 levels) in <top (required)>'

  33) RecurringGroupParser should parse aa a aaa
     Failure/Error: is_expected.to parse "a\na\n\na\n\na\na\na"
       expected BLOCK to be able to parse "a\na\n\na\n\na\na\na"
     # ./parser.rb:161:in `block (2 levels) in <top (required)>'

  34) RecurringGroupParser should parse aaa a aaa
     Failure/Error: is_expected.to parse "a\naa\n\na\n\na\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\n\na\na\na"
     # ./parser.rb:165:in `block (2 levels) in <top (required)>'

  35) RecurringGroupParser should parse a aa aaa
     Failure/Error: is_expected.to parse "a\n\na\na\n\na\na\na"
       expected BLOCK to be able to parse "a\n\na\na\n\na\na\na"
     # ./parser.rb:169:in `block (2 levels) in <top (required)>'

  36) RecurringGroupParser should parse aa aa aaa
     Failure/Error: is_expected.to parse "a\na\n\na\na\n\na\na\na"
       expected BLOCK to be able to parse "a\na\n\na\na\n\na\na\na"
     # ./parser.rb:173:in `block (2 levels) in <top (required)>'

  37) RecurringGroupParser should parse aaa aa aaa
     Failure/Error: is_expected.to parse "a\naa\n\na\na\n\na\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\na\n\na\na\na"
     # ./parser.rb:177:in `block (2 levels) in <top (required)>'

  38) RecurringGroupParser should parse a aaa aaa
     Failure/Error: is_expected.to parse "a\n\na\naa\n\na\na\na"
       expected BLOCK to be able to parse "a\n\na\naa\n\na\na\na"
     # ./parser.rb:181:in `block (2 levels) in <top (required)>'

  39) RecurringGroupParser should parse aa aaa aaa
     Failure/Error: is_expected.to parse "a\na\n\na\naa\n\na\na\na"
       expected BLOCK to be able to parse "a\na\n\na\naa\n\na\na\na"
     # ./parser.rb:185:in `block (2 levels) in <top (required)>'

  40) RecurringGroupParser should parse aaa aaa aaa
     Failure/Error: is_expected.to parse "a\naa\n\na\naa\n\na\na\na"
       expected BLOCK to be able to parse "a\naa\n\na\naa\n\na\na\na"
     # ./parser.rb:189:in `block (2 levels) in <top (required)>'

Finished in 0.01702 seconds (files took 0.26725 seconds to load)
40 examples, 40 failures

请参阅 this question 使用 Parslet 解析缩进。

解析 markdown 缩进代码块

Parse markdown indented code block

ruby

parsing

markdown

parslet