为每个键加载带有行号的YAML

Question

假设我有一个YAML文件，如下所示：

en：错误：#一些评论格式："%｛attribute｝%｛message｝"#再来一条评论消息："1"："消息1"2"："消息2"long_error_message：|这是一个多行消息日期：格式："YYYY-MM-DD"

我怎么能把它读成这样的Ruby Hash呢？

{
  'en': {
    'errors': {
      'format': { value: '%{attribute} %{message}', line: 4 }
      'messages': {
        '1': { value: 'Message 1', line: 8 },
        '2': { value: 'Message 2', line: 9 }
      }
      'long_error_message' : { value: "This is anmultiline message", line: 11 }
    },
    'date': {
      'format': { value: 'YYYY-MM-DD', line: 16 }
    }
  }
}

我尝试过使用YAML中提到的技巧：找到键的行号？作为一个起点，并实现了Psych::Handler，但我觉得我必须重写Psych中的许多代码才能使其发挥作用。

你知道我该怎么解决这个问题吗？

Answer 1

看起来您想要获取任何作为映射值的标量值，并将其替换为具有包含原始值的value密钥和具有行号的line密钥的哈希。

以下方法几乎可行，主要问题是多行字符串，其中给定的行号是Yaml中下一个内容的开始。问题是，当调用处理程序scalar方法时，解析器已经超出了感兴趣的标量，因此mark在知道标量已经结束时给出了位置行。在示例中的大多数情况下，这并不重要，但对于多行大小写，它给出了错误的值。如果不深入Psych C代码，我看不出有任何方法可以从mark中获得标量开头的解析器信息。

require 'psych'
# Psych's first step is to parse the Yaml into an AST of Node objects
# so we open the Node class and add a way to track the line.
class Psych::Nodes::Node
  attr_accessor :line
end
# We need to provide a handler that will add the line to the node
# as it is parsed. TreeBuilder is the "usual" handler, that
# creates the AST.
class LineNumberHandler < Psych::TreeBuilder
  # The handler needs access to the parser in order to call mark
  attr_accessor :parser
  # We are only interested in scalars, so here we override 
  # the method so that it calls mark and adds the line info
  # to the node.
  def scalar value, anchor, tag, plain, quoted, style
    mark = parser.mark
    s = super
    s.line = mark.line
    s
  end
end
# The next step is to convert the AST to a Ruby object.
# Psych does this using the visitor pattern with the ToRuby
# visitor. Here we patch ToRuby rather than inherit from it
# as it makes the last step a little easier.
class Psych::Visitors::ToRuby
  # This is the method for creating hashes. There may be problems
  # with Yaml mappings that have tags.
  def revive_hash hash, o
    o.children.each_slice(2) { |k,v|
      key = accept(k)
      val = accept(v)
      # This is the important bit. If the value is a scalar,
      # we replace it with the desired hash.
      if v.is_a? ::Psych::Nodes::Scalar
        val = { "value" => val, "line" => v.line + 1} # line is 0 based, so + 1
      end
      # Code dealing with << (for merging hashes) omitted.
      # If you need this you will probably need to copy it
      # in here. See the method:
      # https://github.com/tenderlove/psych/blob/v2.0.13/lib/psych/visitors/to_ruby.rb#L333-L365
      hash[key] = val
    }
    hash
  end
end
yaml = get_yaml_from_wherever
# Put it all together    
handler = LineNumberHandler.new
parser =  Psych::Parser.new(handler)
# Provide the handler with a reference to the parser
handler.parser = parser
# The actual parsing
parser.parse yaml
# We patched ToRuby rather than inherit so we can use to_ruby here
puts handler.root.to_ruby

Answer 2

我建议您选择@matt的解决方案。此外，它更为谨慎，能够正确地处理标量

---

诀窍可能是猴痘TreeBuilder#scalar方法：

y='
en:
  errors:
    # Some comment
    format: "%{attribute} %{message}"
    # One more comment
    messages:
      "1": "Message 1"
      "2": "Message 2"
  long_error_message: |
    This is a
    multiline message
  date:
    format: "YYYY-MM-DD"'
require 'yaml'
yphc = Class.new(YAML.parser.handler.class) do
  def scalar value, anchor, tag, plain, quoted, style
    value = { value: value, line: $line } if style > 1 
    $line = $parser.mark.line + 1  # handle multilines properly
    super value, anchor, tag, plain, quoted, style
  end 
end
$parser = Psych::Parser.new(yphc.new)
# more careful handling required for multidocs    
result = $parser.parse(y).handler.root.to_ruby[0]

实际上，我们差不多完成了。唯一剩下的就是在leaves only中留下带有行号的修补值。我并没有故意把这个逻辑放在解析内容中。

def unmark_keys hash
  hash.map do |k,v|
    [k.is_a?(Hash) ? k[:value] : k, v.is_a?(Hash) ? unmark_keys(v) : v]
  end.to_h
end
p unmark_keys result
#⇒ {"en"=>
#⇒   {"errors"=>
#⇒     {
#⇒       "format"=>{:value=>"%{attribute} %{message}", :line=>4},
#⇒       "messages"=>
#⇒          {
#⇒            "1"=>{:value=>"Message 1", :line=>8}, 
#⇒            "2"=>{:value=>"Message 2", :line=>9}
#⇒       }
#⇒     }, 
#⇒     "long_error_message"=>{
#⇒        :value=>"This is anmultiline messagen", :line=>11
#⇒     }, 
#⇒     "date"=>{"format"=>{:value=>"YYYY-MM-DD", :line=>16}}
#⇒   }
#⇒ }

当然，人们可能想要去掉全局变量等。我试图保持核心实现尽可能干净。

我们开始吧。希望能有所帮助。

UPD感谢@matt，上面的代码在标量上失败：

key1:
  val1
key2: val2

这种语法是YAML允许的，但上面的方法没有机会正确处理它。不会为此返回任何行。除了令人烦恼的缺乏标量支持之外，其他任何事情都会正确地报告行，请参阅对此答案的评论以了解更多详细信息。

Answer 3

我采用@matt的解决方案，创建了一个不需要手动补丁的版本。它还处理跨多行的值和YAML的<<运算符。

require "psych"
require "pp"
ValueWithLineNumbers = Struct.new(:value, :lines)
class Psych::Nodes::ScalarWithLineNumber < Psych::Nodes::Scalar
  attr_reader :line_number
  def initialize(*args, line_number)
    super(*args)
    @line_number = line_number
  end
end
class Psych::TreeWithLineNumbersBuilder < Psych::TreeBuilder
  attr_accessor :parser
  def scalar(*args)
    node = Psych::Nodes::ScalarWithLineNumber.new(*args, parser.mark.line)
    @last.children << node
    node
  end
end
class Psych::Visitors::ToRubyWithLineNumbers < Psych::Visitors::ToRuby
  def visit_Psych_Nodes_ScalarWithLineNumber(node)
    visit_Psych_Nodes_Scalar(node)
  end
  private
  def revive_hash(hash, node)
    node.children.each_slice(2) do |k, v|
      key = accept(k)
      val = accept(v)
      if v.is_a? Psych::Nodes::ScalarWithLineNumber
        start_line = end_line = v.line_number + 1
        if k.is_a? Psych::Nodes::ScalarWithLineNumber
          start_line = k.line_number + 1
        end
        val = ValueWithLineNumbers.new(val, start_line..end_line)
      end
      if key == SHOVEL && k.tag != "tag:yaml.org,2002:str"
        case v
        when Psych::Nodes::Alias, Psych::Nodes::Mapping
          begin
            hash.merge! val
          rescue TypeError
            hash[key] = val
          end
        when Psych::Nodes::Sequence
          begin
            h = {}
            val.reverse_each do |value|
              h.merge! value
            end
            hash.merge! h
          rescue TypeError
            hash[key] = val
          end
        else
          hash[key] = val
        end
      else
        hash[key] = val
      end
    end
    hash
  end
end
# Usage:
handler = Psych::TreeWithLineNumbersBuilder.new
handler.parser = Psych::Parser.new(handler)
handler.parser.parse(yaml)
ruby_with_line_numbers = 
Psych::Visitors::ToRubyWithLineNumbers.create.accept(handler.root)
pp ruby_with_line_numbers

我已经发布了上面的要点以及一些评论和示例

Answer 4

我们可以通过递归Psych提供的解析哈希并找到每个键的行号来手动添加数字。以下代码将与您指定的结果相匹配。

require 'psych'
def add_line_numbers(lines, hash)
  # Ruby cannot iterate and modify a hash at the same time.
  # So we dup the hash and iterate over the dup.
  iterator = hash.dup
  iterator.each do |key, value|
    if value.is_a?(Hash)
      add_line_numbers(lines, value)
    else
      index = lines.index { |line| line =~ /^s.?*#{key}.?:/ }
      hash[key] = { "value" => value, "line" => (index + 1) }
    end
  end
end
yaml_file = File.expand_path('../foo.yml', __FILE__)
lines = File.readlines(yaml_file)
data = Psych.load(lines.join("n"))
add_line_numbers(lines, data)
puts data