ralsina/tartrazine
1
0
Fork 0
mirror of https://github.com/ralsina/tartrazine.git synced 2024-12-05 00:00:34 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

feat: SVG formatter

Browse Source
This commit is contained in:
Roberto Alsina 2024-09-21 00:17:41 -03:00
parent d26393d8c9
commit 9c70fbf389
10 changed files with 164 additions and 430 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
.ameba.yml
View File

@ -1,9 +1,9 @@
# This configuration file was generated by `ameba --gen-config` # This configuration file was generated by `ameba --gen-config`
# on 2024-09-11 00:56:14 UTC using Ameba version 1.6.1. # on 2024-09-21 14:59:30 UTC using Ameba version 1.6.1.
# The point is for the user to remove these configuration records # The point is for the user to remove these configuration records
# one by one as the reported problems are removed from the code base. # one by one as the reported problems are removed from the code base.
# Problems found: 4 # Problems found: 3
# Run `ameba --only Documentation/DocumentationAdmonition` for details # Run `ameba --only Documentation/DocumentationAdmonition` for details
Documentation/DocumentationAdmonition: Documentation/DocumentationAdmonition:
Description: Reports documentation admonitions Description: Reports documentation admonitions
@ -11,10 +11,24 @@ Documentation/DocumentationAdmonition:
Excluded: Excluded:
- src/lexer.cr - src/lexer.cr
- src/actions.cr - src/actions.cr
- spec/examples/crystal/lexer_spec.cr
Admonitions: Admonitions:
- TODO - TODO
- FIXME - FIXME
- BUG - BUG
Enabled: true Enabled: true
Severity: Warning Severity: Warning
# Problems found: 1
# Run `ameba --only Lint/SpecFilename` for details
Lint/SpecFilename:
Description: Enforces spec filenames to have `_spec` suffix
Excluded:
- spec/examples/crystal/hello.cr
IgnoredDirs:
- spec/support
- spec/fixtures
- spec/data
IgnoredFilenames:
- spec_helper
Enabled: true
Severity: Warning

1
spec/examples/crystal/hello.cr Normal file
View File

@ -0,0 +1 @@
puts "Hello Crystal!"

1
spec/examples/crystal/hello.cr.json Normal file
View File

@ -0,0 +1 @@
[{"type":"Text","value":"puts "},{"type":"LiteralString","value":"\"Hello Crystal!\""},{"type":"Text","value":"\n"}]

413
spec/examples/crystal/lexer.cr
View File

@ -1,413 +0,0 @@
require "./constants/lexers"
require "./heuristics"
require "baked_file_system"
require "crystal/syntax_highlighter"
module Tartrazine
class LexerFiles
extend BakedFileSystem
bake_folder "../lexers", __DIR__
end
# Get the lexer object for a language name
# FIXME: support mimetypes
def self.lexer(name : String? = nil, filename : String? = nil, mimetype : String? = nil) : BaseLexer
return lexer_by_name(name) if name && name != "autodetect"
return lexer_by_filename(filename) if filename
return lexer_by_mimetype(mimetype) if mimetype
RegexLexer.from_xml(LexerFiles.get("/#{LEXERS_BY_NAME["plaintext"]}.xml").gets_to_end)
end
private def self.lexer_by_mimetype(mimetype : String) : BaseLexer
lexer_file_name = LEXERS_BY_MIMETYPE.fetch(mimetype, nil)
raise Exception.new("Unknown mimetype: #{mimetype}") if lexer_file_name.nil?
RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
end
private def self.lexer_by_name(name : String) : BaseLexer
return CrystalLexer.new if name == "crystal"
lexer_file_name = LEXERS_BY_NAME.fetch(name.downcase, nil)
return create_delegating_lexer(name) if lexer_file_name.nil? && name.includes? "+"
raise Exception.new("Unknown lexer: #{name}") if lexer_file_name.nil?
RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
end
private def self.lexer_by_filename(filename : String) : BaseLexer
if filename.ends_with?(".cr")
return CrystalLexer.new
end
candidates = Set(String).new
LEXERS_BY_FILENAME.each do |k, v|
candidates += v.to_set if File.match?(k, File.basename(filename))
end
case candidates.size
when 0
lexer_file_name = LEXERS_BY_NAME["plaintext"]
when 1
lexer_file_name = candidates.first
else
lexer_file_name = self.lexer_by_content(filename)
begin
return self.lexer(lexer_file_name)
rescue ex : Exception
raise Exception.new("Multiple lexers match the filename: #{candidates.to_a.join(", ")}, heuristics suggest #{lexer_file_name} but there is no matching lexer.")
end
end
RegexLexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
end
private def self.lexer_by_content(fname : String) : String?
h = Linguist::Heuristic.from_yaml(LexerFiles.get("/heuristics.yml").gets_to_end)
result = h.run(fname, File.read(fname))
case result
when Nil
raise Exception.new "No lexer found for #{fname}"
when String
result.as(String)
when Array(String)
result.first
end
end
private def self.create_delegating_lexer(name : String) : BaseLexer
language, root = name.split("+", 2)
language_lexer = lexer(language)
root_lexer = lexer(root)
DelegatingLexer.new(language_lexer, root_lexer)
end
# Return a list of all lexers
def self.lexers : Array(String)
LEXERS_BY_NAME.keys.sort!
end
# A token, the output of the tokenizer
alias Token = NamedTuple(type: String, value: String)
abstract class BaseTokenizer
end
class Tokenizer < BaseTokenizer
include Iterator(Token)
property lexer : BaseLexer
property text : Bytes
property pos : Int32 = 0
@dq = Deque(Token).new
property state_stack = ["root"]
def initialize(@lexer : BaseLexer, text : String, secondary = false)
# Respect the `ensure_nl` config option
if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
text += "\n"
end
@text = text.to_slice
end
def next : Iterator::Stop | Token
if @dq.size > 0
return @dq.shift
end
if pos == @text.size
return stop
end
matched = false
while @pos < @text.size
@lexer.states[@state_stack.last].rules.each do |rule|
matched, new_pos, new_tokens = rule.match(@text, @pos, self)
if matched
@pos = new_pos
split_tokens(new_tokens).each { |token| @dq << token }
break
end
end
if !matched
if @text[@pos] == 10u8
@dq << {type: "Text", value: "\n"}
@state_stack = ["root"]
else
@dq << {type: "Error", value: String.new(@text[@pos..@pos])}
end
@pos += 1
break
end
end
self.next
end
# If a token contains a newline, split it into two tokens
def split_tokens(tokens : Array(Token)) : Array(Token)
split_tokens = [] of Token
tokens.each do |token|
if token[:value].includes?("\n")
values = token[:value].split("\n")
values.each_with_index do |value, index|
value += "\n" if index < values.size - 1
split_tokens << {type: token[:type], value: value}
end
else
split_tokens << token
end
end
split_tokens
end
end
alias BaseLexer = Lexer
abstract class Lexer
property config = {
name: "",
priority: 0.0,
case_insensitive: false,
dot_all: false,
not_multiline: false,
ensure_nl: false,
}
property states = {} of String => State
def tokenizer(text : String, secondary = false) : BaseTokenizer
Tokenizer.new(self, text, secondary)
end
end
# This implements a lexer for Pygments RegexLexers as expressed
# in Chroma's XML serialization.
#
# For explanations on what actions and states do
# the Pygments documentation is a good place to start.
# https://pygments.org/docs/lexerdevelopment/
class RegexLexer < BaseLexer
# Collapse consecutive tokens of the same type for easier comparison
# and smaller output
def self.collapse_tokens(tokens : Array(Tartrazine::Token)) : Array(Tartrazine::Token)
result = [] of Tartrazine::Token
tokens = tokens.reject { |token| token[:value] == "" }
tokens.each do |token|
if result.empty?
result << token
next
end
last = result.last
if last[:type] == token[:type]
new_token = {type: last[:type], value: last[:value] + token[:value]}
result.pop
result << new_token
else
result << token
end
end
result
end
def self.from_xml(xml : String) : Lexer
l = RegexLexer.new
lexer = XML.parse(xml).first_element_child
if lexer
config = lexer.children.find { |node|
node.name == "config"
}
if config
l.config = {
name: xml_to_s(config, name) || "",
priority: xml_to_f(config, priority) || 0.0,
not_multiline: xml_to_s(config, not_multiline) == "true",
dot_all: xml_to_s(config, dot_all) == "true",
case_insensitive: xml_to_s(config, case_insensitive) == "true",
ensure_nl: xml_to_s(config, ensure_nl) == "true",
}
end
rules = lexer.children.find { |node|
node.name == "rules"
}
if rules
# Rules contains states 🤷
rules.children.select { |node|
node.name == "state"
}.each do |state_node|
state = State.new
state.name = state_node["name"]
if l.states.has_key?(state.name)
raise Exception.new("Duplicate state: #{state.name}")
else
l.states[state.name] = state
end
# And states contain rules 🤷
state_node.children.select { |node|
node.name == "rule"
}.each do |rule_node|
case rule_node["pattern"]?
when nil
if rule_node.first_element_child.try &.name == "include"
rule = IncludeStateRule.new(rule_node)
else
rule = UnconditionalRule.new(rule_node)
end
else
rule = Rule.new(rule_node,
multiline: !l.config[:not_multiline],
dotall: l.config[:dot_all],
ignorecase: l.config[:case_insensitive])
end
state.rules << rule
end
end
end
end
l
end
end
# A lexer that takes two lexers as arguments. A root lexer
# and a language lexer. Everything is scalled using the
# language lexer, afterwards all `Other` tokens are lexed
# using the root lexer.
#
# This is useful for things like template languages, where
# you have Jinja + HTML or Jinja + CSS and so on.
class DelegatingLexer < Lexer
property language_lexer : BaseLexer
property root_lexer : BaseLexer
def initialize(@language_lexer : BaseLexer, @root_lexer : BaseLexer)
end
def tokenizer(text : String, secondary = false) : DelegatingTokenizer
DelegatingTokenizer.new(self, text, secondary)
end
end
# This Tokenizer works with a DelegatingLexer. It first tokenizes
# using the language lexer, and "Other" tokens are tokenized using
# the root lexer.
class DelegatingTokenizer < BaseTokenizer
include Iterator(Token)
@dq = Deque(Token).new
@language_tokenizer : BaseTokenizer
def initialize(@lexer : DelegatingLexer, text : String, secondary = false)
# Respect the `ensure_nl` config option
if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
text += "\n"
end
@language_tokenizer = @lexer.language_lexer.tokenizer(text, true)
end
def next : Iterator::Stop | Token
if @dq.size > 0
return @dq.shift
end
token = @language_tokenizer.next
if token.is_a? Iterator::Stop
return stop
elsif token.as(Token).[:type] == "Other"
root_tokenizer = @lexer.root_lexer.tokenizer(token.as(Token).[:value], true)
root_tokenizer.each do |root_token|
@dq << root_token
end
else
@dq << token.as(Token)
end
self.next
end
end
# A Lexer state. A state has a name and a list of rules.
# The state machine has a state stack containing references
# to states to decide which rules to apply.
struct State
property name : String = ""
property rules = [] of BaseRule
def +(other : State)
new_state = State.new
new_state.name = Random.base58(8)
new_state.rules = rules + other.rules
new_state
end
end
class CustomCrystalHighlighter < Crystal::SyntaxHighlighter
@tokens = [] of Token
def render_delimiter(&block)
@tokens << {type: "LiteralString", value: block.call.to_s}
end
def render_interpolation(&block)
@tokens << {type: "LiteralStringInterpol", value: "\#{"}
@tokens << {type: "Text", value: block.call.to_s}
@tokens << {type: "LiteralStringInterpol", value: "}"}
end
def render_string_array(&block)
@tokens << {type: "LiteralString", value: block.call.to_s}
end
# ameba:disable Metrics/CyclomaticComplexity
def render(type : TokenType, value : String)
case type
when .comment?
@tokens << {type: "Comment", value: value}
when .number?
@tokens << {type: "LiteralNumber", value: value}
when .char?
@tokens << {type: "LiteralStringChar", value: value}
when .symbol?
@tokens << {type: "LiteralStringSymbol", value: value}
when .const?
@tokens << {type: "NameConstant", value: value}
when .string?
@tokens << {type: "LiteralString", value: value}
when .ident?
@tokens << {type: "NameVariable", value: value}
when .keyword?, .self?
@tokens << {type: "NameKeyword", value: value}
when .primitive_literal?
@tokens << {type: "Literal", value: value}
when .operator?
@tokens << {type: "Operator", value: value}
when Crystal::SyntaxHighlighter::TokenType::DELIMITED_TOKEN, Crystal::SyntaxHighlighter::TokenType::DELIMITER_START, Crystal::SyntaxHighlighter::TokenType::DELIMITER_END
@tokens << {type: "LiteralString", value: value}
else
@tokens << {type: "Text", value: value}
end
end
end
class CrystalTokenizer < Tartrazine::BaseTokenizer
include Iterator(Token)
@hl = CustomCrystalHighlighter.new
@lexer : BaseLexer
@iter : Iterator(Token)
# delegate next, to: @iter
def initialize(@lexer : BaseLexer, text : String, secondary = false)
# Respect the `ensure_nl` config option
if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
text += "\n"
end
# Just do the tokenizing
@hl.highlight(text)
@iter = @hl.@tokens.each
end
def next : Iterator::Stop | Token
@iter.next
end
end
class CrystalLexer < BaseLexer
def tokenizer(text : String, secondary = false) : BaseTokenizer
CrystalTokenizer.new(self, text, secondary)
end
end
end

1
spec/examples/crystal/lexer.cr.json
View File

File diff suppressed because one or more lines are too long

9
src/formatter.cr
View File

@ -17,12 +17,19 @@ module Tartrazine
end end
def format(text : String, lexer : Lexer) : String def format(text : String, lexer : Lexer) : String
raise Exception.new("Not implemented") outp = String::Builder.new("")
format(text, lexer, outp)
outp.to_s
end end
# Return the styles, if the formatter supports it. # Return the styles, if the formatter supports it.
def style_defs : String def style_defs : String
raise Exception.new("Not implemented") raise Exception.new("Not implemented")
end end
# Is this line in the highlighted ranges?
def highlighted?(line : Int) : Bool
highlight_lines.any?(&.includes?(line))
end
end end
end end

6
src/formatters/ansi.cr
View File

@ -20,12 +20,6 @@ module Tartrazine
"#{i + 1}".rjust(4).ljust(5) "#{i + 1}".rjust(4).ljust(5)
end end
def format(text : String, lexer : BaseLexer) : String
outp = String::Builder.new("")
format(text, lexer, outp)
outp.to_s
end
def format(text : String, lexer : BaseLexer, outp : IO) : Nil def format(text : String, lexer : BaseLexer, outp : IO) : Nil
tokenizer = lexer.tokenizer(text) tokenizer = lexer.tokenizer(text)
i = 0 i = 0

5
src/formatters/html.cr
View File

@ -134,10 +134,5 @@ module Tartrazine
end end
class_prefix + Abbreviations[token] class_prefix + Abbreviations[token]
end end
# Is this line in the highlighted ranges?
def highlighted?(line : Int) : Bool
highlight_lines.any?(&.includes?(line))
end
end end
end end

129
src/formatters/svg.cr Normal file
View File

@ -0,0 +1,129 @@
require "../constants/token_abbrevs.cr"
require "../formatter"
require "html"
module Tartrazine
def self.to_svg(text : String, language : String,
theme : String = "default-dark",
standalone : Bool = true,
line_numbers : Bool = false) : String
Tartrazine::Svg.new(
theme: Tartrazine.theme(theme),
standalone: standalone,
line_numbers: line_numbers
).format(text, Tartrazine.lexer(name: language))
end
class Svg < Formatter
property highlight_lines : Array(Range(Int32, Int32)) = [] of Range(Int32, Int32)
property line_number_id_prefix : String = "line-"
property line_number_start : Int32 = 1
property tab_width = 8
property? line_numbers : Bool = false
property? linkable_line_numbers : Bool = true
property? standalone : Bool = false
property weight_of_bold : Int32 = 600
property fs : Int32
property ystep : Int32
property theme : Theme
def initialize(@theme : Theme = Tartrazine.theme("default-dark"), *,
@highlight_lines = [] of Range(Int32, Int32),
@class_prefix : String = "",
@line_number_id_prefix = "line-",
@line_number_start = 1,
@tab_width = 8,
@line_numbers : Bool = false,
@linkable_line_numbers : Bool = true,
@standalone : Bool = false,
@weight_of_bold : Int32 = 600,
@font_family : String = "monospace",
@font_size : String = "14px")
if font_size.ends_with? "px"
@fs = font_size[0...-2].to_i
else
@fs = font_size.to_i
end
@ystep = @fs + 5
end
def format(text : String, lexer : BaseLexer, io : IO) : Nil
pre, post = wrap_standalone
io << pre if standalone?
format_text(text, lexer, io)
io << post if standalone?
end
# Wrap text into a full HTML document, including the CSS for the theme
def wrap_standalone
output = String.build do |outp|
outp << %(<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.0//EN" "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
<svg xmlns="http://www.w3.org/2000/svg">
<g font-family="#{self.@font_family}" font-size="#{self.@font_size}">)
end
{output.to_s, "</g></svg>"}
end
private def line_label(i : Int32, x : Int32, y : Int32) : String
line_label = "#{i + 1}".rjust(4).ljust(5)
line_style = highlighted?(i + 1) ? "font-weight=\"#{@weight_of_bold}\"" : ""
line_id = linkable_line_numbers? ? "id=\"#{line_number_id_prefix}#{i + 1}\"" : ""
%(<text #{line_style} #{line_id} x="#{4*ystep}" y="#{y}" text-anchor="end">#{line_label}</text>)
end
def format_text(text : String, lexer : BaseLexer, outp : IO)
x = 0
y = ystep
i = 0
line_x = x
line_x += 5 * ystep if line_numbers?
tokenizer = lexer.tokenizer(text)
outp << line_label(i, x, y) if line_numbers?
outp << %(<text x="#{line_x}" y="#{y}" xml:space="preserve">)
tokenizer.each do |token|
if token[:value].ends_with? "\n"
outp << "<tspan #{get_style(token[:type])}>#{HTML.escape(token[:value][0...-1])}</tspan>"
outp << "</text>"
x = 0
y += ystep
i += 1
outp << line_label(i, x, y) if line_numbers?
outp << %(<text x="#{line_x}" y="#{y}" xml:space="preserve">)
else
outp << "<tspan#{get_style(token[:type])}>#{HTML.escape(token[:value])}</tspan>"
x += token[:value].size * ystep
end
end
outp << "</text>"
end
# Given a token type, return the style.
def get_style(token : String) : String
if !theme.styles.has_key? token
# Themes don't contain information for each specific
# token type. However, they may contain information
# for a parent style. Worst case, we go to the root
# (Background) style.
parent = theme.style_parents(token).reverse.find { |dad|
theme.styles.has_key?(dad)
}
theme.styles[token] = theme.styles[parent]
end
output = String.build do |outp|
style = theme.styles[token]
outp << " fill=\"##{style.color.try &.hex}\"" if style.color
# No support for background color or border in SVG
outp << " font-weight=\"#{@weight_of_bold}\"" if style.bold
outp << " font-weight=\"normal\"" if style.bold == false
outp << " font-style=\"italic\"" if style.italic
outp << " font-style=\"normal\"" if style.italic == false
outp << " text-decoration=\"underline\"" if style.underline
outp << " text-decoration=\"none" if style.underline == false
end
output
end
end
end

9
src/main.cr
View File

@ -11,6 +11,8 @@ Usage:
tartrazine -f html -t theme --css tartrazine -f html -t theme --css
tartrazine FILE -f terminal [-t theme][-l lexer][--line-numbers] tartrazine FILE -f terminal [-t theme][-l lexer][--line-numbers]
[-o output] [-o output]
tartrazine FILE -f svg [-t theme][--standalone][--line-numbers]
[-l lexer][-o output]
tartrazine FILE -f json [-o output] tartrazine FILE -f json [-o output]
tartrazine --list-themes tartrazine --list-themes
tartrazine --list-lexers tartrazine --list-lexers
@ -18,7 +20,7 @@ Usage:
tartrazine --version tartrazine --version
Options: Options:
-f <formatter> Format to use (html, terminal, json) -f <formatter> Format to use (html, terminal, json, svg)
-t <theme> Theme to use, see --list-themes [default: default-dark] -t <theme> Theme to use, see --list-themes [default: default-dark]
-l <lexer> Lexer (language) to use, see --list-lexers. Use more than -l <lexer> Lexer (language) to use, see --list-lexers. Use more than
one lexer with "+" (e.g. jinja+yaml) [default: autodetect] one lexer with "+" (e.g. jinja+yaml) [default: autodetect]
@ -71,6 +73,11 @@ if options["-f"]
formatter.theme = theme formatter.theme = theme
when "json" when "json"
formatter = Tartrazine::Json.new formatter = Tartrazine::Json.new
when "svg"
formatter = Tartrazine::Svg.new
formatter.standalone = options["--standalone"] != nil
formatter.line_numbers = options["--line-numbers"] != nil
formatter.theme = theme
else else
puts "Invalid formatter: #{formatter}" puts "Invalid formatter: #{formatter}"
exit 1 exit 1