class Mustache::Parser
[:multi, [:static, “Hi ”], [:mustache, :etag, “thing”], [:static, “!n”]]
$ mustache –tokens test.mustache
mustache(1) command line tool:
You can see the array of tokens for any template with the
[:static, “!n”]]
[:mustache, :etag, “thing”],
[:static, “Hi ”],
[:multi,
Run through the Parser we’ll get these tokens:
Hi {{thing}}!
For example, given this template:
knows which sigil corresponds to which tag type.
raises SyntaxError if there is anything it doesn’t understand and
converting it into an array of tokens and, really, expressions. It
The Parser is responsible for taking a string template and
def self.add_type(*types, &block)
The provided block will be evaluated against the current instance of
* pre_match_position - Location of the scanner before a match was made
* padding - Indentation whitespace from the currently-parsed line
* fetch- A mustache context fetch expression for the content
* content - The raw content of the tag
Requires a block, which will be sent the following parameters:
Add a supported sigil type (with optional aliases) to the Parser.
def self.add_type(*types, &block) types = types.map(&:to_s) type, *aliases = types method_name = "scan_tag_#{type}".to_sym define_method(method_name, &block) aliases.each { |a| alias_method "scan_tag_#{a}", method_name } types.each { |t| VALID_TYPES << t unless VALID_TYPES.include?(t) } @valid_types = nil end
def self.valid_types
def self.valid_types @valid_types ||= Regexp.new(VALID_TYPES.map { |t| Regexp.escape(t) }.join('|') ) end
def compile(template)
def compile(template) @encoding = nil if template.respond_to?(:encoding) @encoding = template.encoding template = template.dup.force_encoding("BINARY") end # Keeps information about opened sections. @sections = [] @result = [:multi] @scanner = StringScanner.new(template) # Scan until the end of the template. until @scanner.eos? scan_tags || scan_text end unless @sections.empty? # We have parsed the whole file, but there's still opened sections. type, pos, _ = @sections.pop error "Unclosed section #{type.inspect}", pos end @result end
def content_tags type, current_ctag
def content_tags type, current_ctag if ANY_CONTENT.include?(type) r = /\s*#{regexp(type)}?#{regexp(current_ctag)}/ scan_until_exclusive(r) else @scanner.scan(ALLOWED_CONTENT) end end
def ctag
def ctag @ctag ||= '}}' end
def dispatch_based_on_type type, content, fetch, padding, pre_match_position
def dispatch_based_on_type type, content, fetch, padding, pre_match_position send("scan_tag_#{type}", content, fetch, padding, pre_match_position) end
def error(message, pos = position)
error - other details such as line number and position are
Raises a SyntaxError. The message should be the name of the
def error(message, pos = position) raise SyntaxError.new(message, pos) end
def find_closing_tag scanner, current_ctag
def find_closing_tag scanner, current_ctag error "Unclosed tag" unless scanner.scan(regexp(current_ctag)) end
def initialize(options = {})
Accepts an options hash which does nothing but may be used in
def initialize(options = {}) @options = {} end
def offset
def offset position[0, 2] end
def otag
def otag @otag ||= '{{' end
def position
def position # The rest of the current line rest = @scanner.check_until(/\n|\Z/).to_s.chomp # What we have parsed so far parsed = @scanner.string[0...@scanner.pos] lines = parsed.split("\n") [ lines.size, lines.last.size - 1, lines.last + rest ] end
def regexp(thing)
Used to quickly convert a string into a regular expression
def regexp(thing) /#{Regexp.escape(thing)}/ end
def scan_tag_ content, fetch, padding, pre_match_position
This function handles the cases where the scanned tag does not have
def scan_tag_ content, fetch, padding, pre_match_position @result << [:mustache, :etag, fetch, offset] end
def scan_tag_block content, fetch, padding, pre_match_position
def scan_tag_block content, fetch, padding, pre_match_position block = [:multi] @result << [:mustache, :section, fetch, offset, block] @sections << [content, position, @result] @result = block end
def scan_tag_close content, fetch, padding, pre_match_position
def scan_tag_close content, fetch, padding, pre_match_position section, pos, result = @sections.pop raw = @scanner.pre_match[pos[3]...pre_match_position] + padding (@result = result).last << raw << [self.otag, self.ctag] if section.nil? error "Closing unopened #{content.inspect}" elsif section != content error "Unclosed section #{section.inspect}", pos end end
def scan_tag_comment content, fetch, padding, pre_match_position
def scan_tag_comment content, fetch, padding, pre_match_position end
def scan_tag_delimiter content, fetch, padding, pre_match_position
def scan_tag_delimiter content, fetch, padding, pre_match_position self.otag, self.ctag = content.split(' ', 2) end
def scan_tag_inverted content, fetch, padding, pre_match_position
def scan_tag_inverted content, fetch, padding, pre_match_position block = [:multi] @result << [:mustache, :inverted_section, fetch, offset, block] @sections << [content, position, @result] @result = block end
def scan_tag_open_partial content, fetch, padding, pre_match_position
def scan_tag_open_partial content, fetch, padding, pre_match_position @result << [:mustache, :partial, content, offset, padding] end
def scan_tag_unescaped content, fetch, padding, pre_match_position
def scan_tag_unescaped content, fetch, padding, pre_match_position @result << [:mustache, :utag, fetch, offset] end
def scan_tags
def scan_tags # Scan until we hit an opening delimiter. start_of_line = @scanner.beginning_of_line? pre_match_position = @scanner.pos last_index = @result.length return unless @scanner.scan(/([ \t]*)?#{Regexp.escape(otag)}/) padding = @scanner[1] || '' # Don't touch the preceding whitespace unless we're matching the start # of a new line. unless start_of_line @result << [:static, padding] unless padding.empty? pre_match_position += padding.length padding = '' end # Since {{= rewrites ctag, we store the ctag which should be used # when parsing this specific tag. current_ctag = self.ctag type = @scanner.scan(self.class.valid_types) @scanner.skip(/\s*/) # ANY_CONTENT tags allow any character inside of them, while # other tags (such as variables) are more strict. content = content_tags(type, current_ctag) # We found {{ but we can't figure out what's going on inside. error "Illegal content in tag" if content.empty? fetch = [:mustache, :fetch, content.split('.')] prev = @result dispatch_based_on_type(type, content, fetch, padding, pre_match_position) # The closing } in unescaped tags is just a hack for # aesthetics. type = "}" if type == "{" # Skip whitespace and any balancing sigils after the content # inside this tag. @scanner.skip(/\s+/) @scanner.skip(regexp(type)) if type find_closing_tag(@scanner, current_ctag) # If this tag was the only non-whitespace content on this line, strip # the remaining whitespace. If not, but we've been hanging on to padding # from the beginning of the line, re-insert the padding as static text. if start_of_line && !@scanner.eos? if @scanner.peek(2) =~ /\r?\n/ && SKIP_WHITESPACE.include?(type) @scanner.skip(/\r?\n/) else prev.insert(last_index, [:static, padding]) unless padding.empty? end end # Store off the current scanner position now that we've closed the tag # and consumed any irrelevant whitespace. @sections.last[1] << @scanner.pos unless @sections.empty? return unless @result == [:multi] end
def scan_text
def scan_text text = scan_until_exclusive(/(^[ \t]*)?#{Regexp.escape(otag)}/) if text.nil? # Couldn't find any otag, which means the rest is just static text. text = @scanner.rest # Mark as done. @scanner.terminate end text.force_encoding(@encoding) if @encoding @result << [:static, text] unless text.empty? end
def scan_until_exclusive(regexp)
*excluding* the end of the match, advancing the scan pointer to that
Scans the string until the pattern is matched. Returns the substring
def scan_until_exclusive(regexp) pos = @scanner.pos if @scanner.scan_until(regexp) @scanner.pos -= @scanner.matched.size @scanner.pre_match[pos..-1] end end