puttext 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.codeclimate.yml +19 -0
- data/.gitattributes +17 -0
- data/.gitignore +50 -0
- data/.rspec +1 -0
- data/.rubocop.yml +26 -0
- data/.ruby-version +1 -0
- data/.travis.yml +18 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +68 -0
- data/LICENSE +21 -0
- data/README.md +82 -0
- data/Rakefile +8 -0
- data/bin/puttext +6 -0
- data/lib/puttext.rb +6 -0
- data/lib/puttext/cmdline.rb +71 -0
- data/lib/puttext/extractor.rb +114 -0
- data/lib/puttext/parser/base.rb +32 -0
- data/lib/puttext/parser/ruby.rb +114 -0
- data/lib/puttext/parser/slim.rb +61 -0
- data/lib/puttext/po_entry.rb +181 -0
- data/lib/puttext/po_file.rb +53 -0
- data/puttext.gemspec +37 -0
- data/spec/fixtures/extractor_fixtures/another_file.php +0 -0
- data/spec/fixtures/extractor_fixtures/file_1.rb +0 -0
- data/spec/fixtures/extractor_fixtures/file_2.rb +0 -0
- data/spec/fixtures/extractor_fixtures/random_file.txt +0 -0
- data/spec/fixtures/extractor_fixtures/subfolder/subfile.py +0 -0
- data/spec/fixtures/extractor_fixtures/subfolder/subfile_1.rb +0 -0
- data/spec/fixtures/extractor_fixtures/subfolder/subfile_2.rb +0 -0
- data/spec/fixtures/parser_base_shared_fixture.rb +3 -0
- data/spec/shared/parser_base_shared.rb +38 -0
- data/spec/spec_helper.rb +12 -0
- data/spec/unit/extractor_spec.rb +168 -0
- data/spec/unit/parser/ruby_spec.rb +176 -0
- data/spec/unit/parser/slim_spec.rb +86 -0
- data/spec/unit/po_entry_spec.rb +327 -0
- data/spec/unit/po_file_spec.rb +53 -0
- metadata +199 -0
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative '../po_entry'
|
4
|
+
|
5
|
+
module PutText
|
6
|
+
module Parser
|
7
|
+
# Thrown when any error parsing a file occurs
|
8
|
+
class ParseError < StandardError; end
|
9
|
+
|
10
|
+
class Base
|
11
|
+
# Parse gettext strings from a file in the path.
|
12
|
+
# @param [String] path the path of the file to parse.
|
13
|
+
# @return [Array<POEntry>] an array of POEntry objects extracted
|
14
|
+
# from the given file.
|
15
|
+
def strings_from_file(path)
|
16
|
+
strings_from_source(File.read(path), filename: path)
|
17
|
+
end
|
18
|
+
|
19
|
+
# @abstract Subclass is expected to implement #strings_from_source
|
20
|
+
# @!method strings_from_source(source, opts)
|
21
|
+
# Parse gettext strings from a given snippet of source code.
|
22
|
+
# @param [String] source the snippet of source code to parse.
|
23
|
+
# @param [Hash] opts
|
24
|
+
# @option opts [String] :filename path of the file being parsed.
|
25
|
+
# Defaults to "(string)".
|
26
|
+
# @option opts [Integer] :first_line number of the first line being
|
27
|
+
# parsed. Defaults to 1.
|
28
|
+
# @return [Array<POEntry>] an array of POEntry objects
|
29
|
+
# extracted from the given source code.
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,114 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'base'
|
4
|
+
require_relative '../po_entry'
|
5
|
+
|
6
|
+
require 'parser/current'
|
7
|
+
|
8
|
+
# opt-in to most recent Parser AST format:
|
9
|
+
Parser::Builders::Default.emit_lambda = true
|
10
|
+
Parser::Builders::Default.emit_procarg0 = true
|
11
|
+
|
12
|
+
module PutText
|
13
|
+
module Parser
|
14
|
+
class Ruby < Base
|
15
|
+
METHODS = {
|
16
|
+
gettext: :regular,
|
17
|
+
_: :regular,
|
18
|
+
ngettext: :plural,
|
19
|
+
n_: :plural,
|
20
|
+
sgettext: :context_sep,
|
21
|
+
s_: :context_sep,
|
22
|
+
nsgettext: :context_sep_plural,
|
23
|
+
ns_: :context_sep_plural,
|
24
|
+
pgettext: :context,
|
25
|
+
p_: :context,
|
26
|
+
npgettext: :context_plural,
|
27
|
+
np_: :context_plural
|
28
|
+
}.freeze
|
29
|
+
|
30
|
+
PARAMS = {
|
31
|
+
regular: %i(msgid),
|
32
|
+
plural: %i(msgid msgid_plural),
|
33
|
+
context: %i(msgctxt msgid),
|
34
|
+
context_plural: %i(msgctxt msgid msgid_plural),
|
35
|
+
context_sep: %i(msgid separator),
|
36
|
+
context_sep_plural: %i(msgid msgid_plural _ separator)
|
37
|
+
}.freeze
|
38
|
+
|
39
|
+
def initialize
|
40
|
+
@ruby_parser = ::Parser::CurrentRuby.new
|
41
|
+
end
|
42
|
+
|
43
|
+
def strings_from_source(source, filename: '(string)', first_line: 1)
|
44
|
+
buffer = ::Parser::Source::Buffer.new(filename, first_line)
|
45
|
+
buffer.source = source
|
46
|
+
|
47
|
+
@ruby_parser.reset
|
48
|
+
ast = @ruby_parser.parse(buffer)
|
49
|
+
|
50
|
+
if ast.is_a? ::Parser::AST::Node
|
51
|
+
find_strings_in_ast(ast)
|
52
|
+
else
|
53
|
+
[]
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
private
|
58
|
+
|
59
|
+
def string_from_ast_node(ast_node)
|
60
|
+
return if ast_node.nil?
|
61
|
+
|
62
|
+
case ast_node.type
|
63
|
+
when :str
|
64
|
+
ast_node.children[0]
|
65
|
+
else
|
66
|
+
raise ParseError,
|
67
|
+
format('unsupported AST node type: %s', ast_node.type)
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
def po_entry_from_ast_node(ast_node, type)
|
72
|
+
filename = ast_node.location.expression.source_buffer.name
|
73
|
+
line = ast_node.location.line
|
74
|
+
|
75
|
+
entry_attrs = { references: ["#{filename}:#{line}"] }
|
76
|
+
|
77
|
+
PARAMS[type].each_with_index do |name, index|
|
78
|
+
next if name == :_ # skip parameters named _
|
79
|
+
|
80
|
+
param = string_from_ast_node(ast_node.children[index + 2])
|
81
|
+
entry_attrs[name] = param if param
|
82
|
+
end
|
83
|
+
|
84
|
+
PutText::POEntry.new(entry_attrs)
|
85
|
+
end
|
86
|
+
|
87
|
+
def find_strings_in_ast(ast_node)
|
88
|
+
entries = []
|
89
|
+
|
90
|
+
if ast_node.type == :send && METHODS[ast_node.children[1]]
|
91
|
+
entries << po_entry_from_ast_node(
|
92
|
+
ast_node,
|
93
|
+
METHODS[ast_node.children[1]]
|
94
|
+
)
|
95
|
+
else
|
96
|
+
entries += find_strings_in_each_ast(ast_node.children)
|
97
|
+
end
|
98
|
+
|
99
|
+
entries
|
100
|
+
end
|
101
|
+
|
102
|
+
def find_strings_in_each_ast(ast_nodes)
|
103
|
+
entries = []
|
104
|
+
|
105
|
+
ast_nodes.each do |node|
|
106
|
+
next unless node.is_a? ::Parser::AST::Node
|
107
|
+
entries += find_strings_in_ast(node)
|
108
|
+
end
|
109
|
+
|
110
|
+
entries
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
end
|
@@ -0,0 +1,61 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'base'
|
4
|
+
require_relative 'ruby'
|
5
|
+
|
6
|
+
begin
|
7
|
+
require 'slim'
|
8
|
+
|
9
|
+
module PutText
|
10
|
+
module Parser
|
11
|
+
class Slim < Base
|
12
|
+
def initialize
|
13
|
+
@ruby_parser = PutText::Parser::Ruby.new
|
14
|
+
@slim_engine = Engine.new
|
15
|
+
end
|
16
|
+
|
17
|
+
def strings_from_source(source, filename: '(string)', first_line: 1)
|
18
|
+
slim_ruby_code = @slim_engine.call(source)
|
19
|
+
|
20
|
+
@ruby_parser.strings_from_source(
|
21
|
+
slim_ruby_code,
|
22
|
+
filename: filename,
|
23
|
+
first_line: first_line
|
24
|
+
)
|
25
|
+
end
|
26
|
+
|
27
|
+
class IgnoreEmbedded < ::Slim::Filter
|
28
|
+
def on_slim_embedded(_name, body)
|
29
|
+
newlines = count_newlines(body)
|
30
|
+
|
31
|
+
node = [:multi]
|
32
|
+
newlines.times { node.push [:newline] }
|
33
|
+
node
|
34
|
+
end
|
35
|
+
|
36
|
+
private
|
37
|
+
|
38
|
+
def count_newlines(body)
|
39
|
+
newlines = 0
|
40
|
+
newlines += 1 if body.first == :newline
|
41
|
+
|
42
|
+
body.each do |el|
|
43
|
+
newlines += count_newlines(el) if el.is_a?(Array)
|
44
|
+
end
|
45
|
+
|
46
|
+
newlines
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
class Engine < ::Slim::Engine
|
51
|
+
replace ::Slim::Embedded, IgnoreEmbedded
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
# rubocop:disable Lint/HandleExceptions
|
58
|
+
rescue LoadError
|
59
|
+
# Optional dependency, do not fail if not found
|
60
|
+
end
|
61
|
+
# rubocop:enable Lint/HandleExceptions
|
@@ -0,0 +1,181 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module PutText
|
4
|
+
class POEntry
|
5
|
+
NS_SEPARATOR = '|'.freeze
|
6
|
+
|
7
|
+
PO_C_STYLE_ESCAPES = {
|
8
|
+
"\n" => '\\n',
|
9
|
+
"\r" => '\\r',
|
10
|
+
"\t" => '\\t',
|
11
|
+
'\\' => '\\\\',
|
12
|
+
'"' => '\\"'
|
13
|
+
}.freeze
|
14
|
+
|
15
|
+
attr_reader :msgid
|
16
|
+
attr_reader :msgid_plural
|
17
|
+
attr_reader :msgctxt
|
18
|
+
attr_reader :references
|
19
|
+
|
20
|
+
# Create a new POEntry
|
21
|
+
#
|
22
|
+
# @param [Hash] attrs
|
23
|
+
# @option attrs [String] :msgid the id of the string (the string that needs
|
24
|
+
# to be translated). Can include a context, separated from the id by
|
25
|
+
# {NS_SEPARATOR} or by the specified :separator.
|
26
|
+
# @option attrs [String] :msgid_plural the pluralized id of the string (the
|
27
|
+
# pluralized string that needs to be translated).
|
28
|
+
# @option attrs [String] :msgctxt the context of the string.
|
29
|
+
# @option attrs [Array<String>] :references a list of files with line
|
30
|
+
# numbers, pointing to where the string was found.
|
31
|
+
# @option attrs [String] :separator the separator of context from id in
|
32
|
+
# :msgid.
|
33
|
+
def initialize(attrs)
|
34
|
+
id, ctx = extract_context(
|
35
|
+
attrs[:msgid], attrs[:separator] || NS_SEPARATOR
|
36
|
+
)
|
37
|
+
|
38
|
+
@msgid = id
|
39
|
+
@msgctxt = attrs[:msgctxt] || ctx
|
40
|
+
@msgid_plural = attrs[:msgid_plural]
|
41
|
+
@references = attrs[:references] || []
|
42
|
+
end
|
43
|
+
|
44
|
+
# Convert the entry to a string representation, to be written to a .po file
|
45
|
+
# @return [String] a string representation of the entry.
|
46
|
+
def to_s
|
47
|
+
str = String.new('')
|
48
|
+
|
49
|
+
# Add comments
|
50
|
+
str = add_comment(str, ':', @references.join(' ')) if references?
|
51
|
+
|
52
|
+
# Add id and context
|
53
|
+
str = add_string(str, 'msgctxt', @msgctxt) if @msgctxt
|
54
|
+
str = add_string(str, 'msgid', @msgid)
|
55
|
+
str = add_string(str, 'msgid_plural', @msgid_plural) if plural?
|
56
|
+
str = add_translations(str)
|
57
|
+
|
58
|
+
str
|
59
|
+
end
|
60
|
+
|
61
|
+
# Check if the entry has any references.
|
62
|
+
# @return [Boolean] whether the entry has any references.
|
63
|
+
def references?
|
64
|
+
!@references.empty?
|
65
|
+
end
|
66
|
+
|
67
|
+
# Check if the entry has a plural form.
|
68
|
+
# @return [Boolean] whether the entry has a plural form.
|
69
|
+
def plural?
|
70
|
+
!@msgid_plural.nil?
|
71
|
+
end
|
72
|
+
|
73
|
+
# Return an object uniquely identifying this entry. The returned object can
|
74
|
+
# be used to find duplicate entries.
|
75
|
+
# @return an object uniquely identifying this entry.
|
76
|
+
def unique_key
|
77
|
+
[@msgid, @msgctxt]
|
78
|
+
end
|
79
|
+
|
80
|
+
# Merge this entry with another entry. Modifies the current entry in place.
|
81
|
+
# Currently, merges only the references, and leaves other attributes of the
|
82
|
+
# current entry untouched.
|
83
|
+
#
|
84
|
+
# @param [POEntry] other_entry the entry to merge with.
|
85
|
+
# @return [POEntry] the merged entry.
|
86
|
+
def merge(other_entry)
|
87
|
+
@references += other_entry.references
|
88
|
+
self
|
89
|
+
end
|
90
|
+
|
91
|
+
def ==(other)
|
92
|
+
@msgid == other.msgid &&
|
93
|
+
@msgid_plural == other.msgid_plural &&
|
94
|
+
@msgctxt == other.msgctxt &&
|
95
|
+
@references == other.references
|
96
|
+
end
|
97
|
+
|
98
|
+
private
|
99
|
+
|
100
|
+
def extract_context(str, separator)
|
101
|
+
parts = str.rpartition(separator)
|
102
|
+
[parts[2], parts[0] == '' ? nil : parts[0]]
|
103
|
+
end
|
104
|
+
|
105
|
+
def add_comment(str, comment_type, value)
|
106
|
+
value.each_line do |line|
|
107
|
+
str << '#'
|
108
|
+
str << comment_type
|
109
|
+
str << ' '
|
110
|
+
str << line
|
111
|
+
str << "\n"
|
112
|
+
end
|
113
|
+
|
114
|
+
str
|
115
|
+
end
|
116
|
+
|
117
|
+
def add_string(str, id, value)
|
118
|
+
str << id
|
119
|
+
str << ' '
|
120
|
+
str << string_to_po(value)
|
121
|
+
str << "\n"
|
122
|
+
end
|
123
|
+
|
124
|
+
def add_translations(str)
|
125
|
+
if plural?
|
126
|
+
add_string(str, 'msgstr[0]', '')
|
127
|
+
add_string(str, 'msgstr[1]', '')
|
128
|
+
else
|
129
|
+
add_string(str, 'msgstr', '')
|
130
|
+
end
|
131
|
+
|
132
|
+
str
|
133
|
+
end
|
134
|
+
|
135
|
+
def string_to_po(str)
|
136
|
+
lines = str.split("\n", -1)
|
137
|
+
|
138
|
+
if lines.empty?
|
139
|
+
'""'
|
140
|
+
elsif lines.length == 1
|
141
|
+
"\"#{po_escape_string(lines[0])}\""
|
142
|
+
else
|
143
|
+
multiline_string_to_po(lines)
|
144
|
+
end
|
145
|
+
end
|
146
|
+
|
147
|
+
def multiline_string_to_po(str_lines)
|
148
|
+
po_str = String.new('""')
|
149
|
+
|
150
|
+
str_lines.each_with_index do |line, index|
|
151
|
+
last = index == str_lines.length - 1
|
152
|
+
add_multiline_str_part(po_str, line, last)
|
153
|
+
end
|
154
|
+
|
155
|
+
po_str
|
156
|
+
end
|
157
|
+
|
158
|
+
def add_multiline_str_part(str, part, last)
|
159
|
+
return if last && part.empty?
|
160
|
+
|
161
|
+
str << "\n\""
|
162
|
+
str << po_escape_string(part)
|
163
|
+
str << '\\n' unless last
|
164
|
+
str << '"'
|
165
|
+
end
|
166
|
+
|
167
|
+
def po_escape_string(str)
|
168
|
+
encoded = String.new('')
|
169
|
+
|
170
|
+
str.each_char do |char|
|
171
|
+
encoded << if PO_C_STYLE_ESCAPES[char]
|
172
|
+
PO_C_STYLE_ESCAPES[char]
|
173
|
+
else
|
174
|
+
char
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
encoded
|
179
|
+
end
|
180
|
+
end
|
181
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module PutText
|
4
|
+
class POFile
|
5
|
+
attr_accessor :entries
|
6
|
+
|
7
|
+
# Create a new POFile
|
8
|
+
# @param [Array<POEntry>] entries an array of POEntry objects, that should
|
9
|
+
# be placed in this file.
|
10
|
+
def initialize(entries)
|
11
|
+
@entries = entries
|
12
|
+
end
|
13
|
+
|
14
|
+
def to_s
|
15
|
+
str_io = StringIO.new
|
16
|
+
write_to(str_io)
|
17
|
+
str_io.string
|
18
|
+
end
|
19
|
+
|
20
|
+
# Write the contents of this file to the specified IO object.
|
21
|
+
# @param [IO] io the IO object to write the contents of the file to.
|
22
|
+
def write_to(io)
|
23
|
+
deduplicate
|
24
|
+
|
25
|
+
@entries.each_with_index do |entry, index|
|
26
|
+
io.write("\n") unless index == 0
|
27
|
+
io.write(entry.to_s)
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def ==(other)
|
32
|
+
@entries.sort == other.entries.sort
|
33
|
+
end
|
34
|
+
|
35
|
+
private
|
36
|
+
|
37
|
+
def deduplicate
|
38
|
+
uniq_entries = {}
|
39
|
+
|
40
|
+
@entries.each do |entry|
|
41
|
+
key = entry.unique_key
|
42
|
+
|
43
|
+
if uniq_entries[key]
|
44
|
+
uniq_entries[key].merge(entry)
|
45
|
+
else
|
46
|
+
uniq_entries[key] = entry
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
@entries = uniq_entries.values
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
data/puttext.gemspec
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'date'
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = 'puttext'
|
7
|
+
s.version = '0.1.0'
|
8
|
+
s.date = Date.today.to_s
|
9
|
+
s.summary = 'Extract gettext strings from Ruby source'
|
10
|
+
s.authors = ['Mantas Norvaiša']
|
11
|
+
s.email = 'mntnorv@gmail.com'
|
12
|
+
s.homepage = 'https://github.com/mntnorv/puttext'
|
13
|
+
s.license = 'MIT'
|
14
|
+
|
15
|
+
s.files = `git ls-files`.split
|
16
|
+
s.executables = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
|
+
s.require_paths = ['lib']
|
18
|
+
|
19
|
+
s.required_ruby_version = '>= 2.0.0'
|
20
|
+
|
21
|
+
s.add_runtime_dependency('parser', '>= 2.4.0.0', '< 3.0')
|
22
|
+
|
23
|
+
# Optional dependencies at runtime, required for development
|
24
|
+
s.add_development_dependency('slim', '~> 3.0')
|
25
|
+
|
26
|
+
# Tools
|
27
|
+
s.add_development_dependency('rake')
|
28
|
+
|
29
|
+
# Testing
|
30
|
+
s.add_development_dependency('rspec', '~> 3.5')
|
31
|
+
s.add_development_dependency('unindent')
|
32
|
+
|
33
|
+
# Linters and code policies
|
34
|
+
s.add_development_dependency('rubocop', '~> 0.46.0')
|
35
|
+
s.add_development_dependency('simplecov')
|
36
|
+
s.add_development_dependency('codeclimate-test-reporter', '~> 1.0.0')
|
37
|
+
end
|