lm_docstache 3.0.3 → 3.0.8
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +40 -0
- data/lib/lm_docstache.rb +1 -1
- data/lib/lm_docstache/document.rb +66 -31
- data/lib/lm_docstache/parser.rb +46 -2
- data/lib/lm_docstache/version.rb +1 -1
- data/spec/example_input/ExampleTemplate.docx +0 -0
- data/spec/integration_spec.rb +5 -29
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b414a4508c323651394880630f25af46409778dfc205ebc5621d72e07a6e69a3
|
4
|
+
data.tar.gz: 896ce5a0ef359f2b3a77646a631b66ef74a67fb6f5d8fa2ac218a3d346b8f0f8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e14266f143047c25ee683b6544ddca31648ac83b51a7a72756f3f01dfa1800353f684d3c1a82e878f523a29ef829389f99c7e4f60b0c6d5c46708eccffc5c36c
|
7
|
+
data.tar.gz: 0f5ee3910f3a77519fec6ee1db604954c49f3ecc5b0e12af4bcc4d7844b0f10bc9ee410070291381fbd90cce25f974c246a8bca6a107b8d63021b8e38ed3cef9
|
data/CHANGELOG.md
CHANGED
@@ -1,5 +1,45 @@
|
|
1
1
|
# Changelog
|
2
2
|
|
3
|
+
## 3.0.8
|
4
|
+
|
5
|
+
#### Bug fixes
|
6
|
+
|
7
|
+
* Fix a bug on `usable_tags` method, so it now properly and expectedly
|
8
|
+
includes conditional tag names that have its opening tag markup as the sole
|
9
|
+
content of paragraphs (which represents conditional blocks where both
|
10
|
+
opening and closing tags are in separate parapraghs sorrounding one or more
|
11
|
+
paragraphs as its conditional block content).
|
12
|
+
|
13
|
+
## 3.0.7
|
14
|
+
|
15
|
+
#### Bug fixes
|
16
|
+
|
17
|
+
* Fix a bug on `usable_tag_names` method, so it now properly and expectedly
|
18
|
+
includes conditional tag names as well, as before.
|
19
|
+
|
20
|
+
## 3.0.6
|
21
|
+
|
22
|
+
#### Bug fixes
|
23
|
+
|
24
|
+
* Fix bug on `LMDocstache::Docstache#unusable_tags` method, where `nil` could be
|
25
|
+
passed to `broken_tags.deleted_at` call.
|
26
|
+
|
27
|
+
## 3.0.5
|
28
|
+
|
29
|
+
#### Bug fixes and improvements
|
30
|
+
|
31
|
+
* Improve the way broken tags are detected, making the algorithm wider in terms
|
32
|
+
detecting broken tags, specially if the broken tag is the opening part of
|
33
|
+
conditional tag blocks (which was being detected before these improvements).
|
34
|
+
* Improve the way the paragraphs with "unusable" tags are traversed and have
|
35
|
+
their same-style texts merged (hence the "unusable" tags becoming usable). So,
|
36
|
+
from now, `w:hyperlink` elements, for instance, are properly processed as
|
37
|
+
well.
|
38
|
+
|
39
|
+
## 3.0.4
|
40
|
+
* Allow replacement `data` argument to be an `Array`. This feature allow to replace blocks
|
41
|
+
in a sequentially order following the sequence of matching blocks order.
|
42
|
+
|
3
43
|
## 3.0.3
|
4
44
|
|
5
45
|
### Bugfix
|
data/lib/lm_docstache.rb
CHANGED
@@ -1,9 +1,9 @@
|
|
1
1
|
require 'nokogiri'
|
2
2
|
require 'zip'
|
3
3
|
require "lm_docstache/version"
|
4
|
+
require "lm_docstache/parser"
|
4
5
|
require "lm_docstache/document"
|
5
6
|
require 'lm_docstache/hide_custom_tags'
|
6
|
-
require "lm_docstache/parser"
|
7
7
|
require "lm_docstache/condition"
|
8
8
|
require "lm_docstache/conditional_block"
|
9
9
|
require "lm_docstache/renderer"
|
@@ -1,7 +1,10 @@
|
|
1
1
|
module LMDocstache
|
2
2
|
class Document
|
3
|
-
|
3
|
+
WHOLE_BLOCK_START_REGEX = /^#{Parser::BLOCK_START_PATTERN}$/
|
4
|
+
GENERAL_TAG_REGEX = /\{\{[\/#^]?(.+?)(?:(\s((?:==|~=))\s?.+?))?\}\}/
|
4
5
|
ROLES_REGEXP = /({{(sig|sigfirm|date|check|text|initial)\|(req|noreq)\|(.+?)}})/
|
6
|
+
BLOCK_CHILDREN_ELEMENTS = 'w|r,w|hyperlink,w|ins,w|del'
|
7
|
+
RUN_LIKE_ELEMENTS = 'w|r,w|ins'
|
5
8
|
|
6
9
|
def initialize(*paths)
|
7
10
|
raise ArgumentError if paths.empty?
|
@@ -34,38 +37,41 @@ module LMDocstache
|
|
34
37
|
|
35
38
|
def tags
|
36
39
|
@documents.values.flat_map do |document|
|
37
|
-
document.text
|
40
|
+
document_text = document.text
|
41
|
+
extract_tag_names(document_text) + extract_tag_names(document_text, :full_block)
|
38
42
|
end
|
39
43
|
end
|
40
44
|
|
41
45
|
def usable_tags
|
42
46
|
@documents.values.reduce([]) do |tags, document|
|
43
47
|
document.css('w|t').reduce(tags) do |document_tags, text_node|
|
44
|
-
|
48
|
+
text = text_node.text
|
49
|
+
document_tags.push(*extract_tag_names(text))
|
50
|
+
document_tags.push(*extract_tag_names(text, :start_block))
|
51
|
+
document_tags.push(*extract_tag_names(text, :full_block))
|
45
52
|
end
|
46
53
|
end
|
47
54
|
end
|
48
55
|
|
49
56
|
def usable_tag_names
|
50
|
-
usable_tags.
|
51
|
-
tag.
|
52
|
-
|
57
|
+
usable_tags.reduce([]) do |memo, tag|
|
58
|
+
next memo if !tag.is_a?(Regexp) && tag =~ ROLES_REGEXP
|
59
|
+
|
60
|
+
tag = unescape_escaped_start_block(tag.source) if tag.is_a?(Regexp)
|
61
|
+
memo << (tag.scan(GENERAL_TAG_REGEX) && $1)
|
53
62
|
end.compact.uniq
|
54
63
|
end
|
55
64
|
|
56
65
|
def unusable_tags
|
57
|
-
|
66
|
+
usable_tags.reduce(tags) do |broken_tags, usable_tag|
|
67
|
+
next broken_tags unless index = broken_tags.index(usable_tag)
|
58
68
|
|
59
|
-
|
60
|
-
index = unusable_tags.index(usable_tag)
|
61
|
-
unusable_tags.delete_at(index) if index
|
69
|
+
broken_tags.delete_at(index) && broken_tags
|
62
70
|
end
|
63
|
-
|
64
|
-
unusable_tags
|
65
71
|
end
|
66
72
|
|
67
73
|
def fix_errors
|
68
|
-
problem_paragraphs.each { |pg|
|
74
|
+
problem_paragraphs.each { |pg| flatten_text_blocks(pg) if pg }
|
69
75
|
end
|
70
76
|
|
71
77
|
def errors?
|
@@ -99,6 +105,28 @@ module LMDocstache
|
|
99
105
|
|
100
106
|
private
|
101
107
|
|
108
|
+
def unescape_escaped_start_block(regex_source_string)
|
109
|
+
regex_source_string
|
110
|
+
.gsub('\\{', '{')
|
111
|
+
.gsub('\\#', '#')
|
112
|
+
.gsub('\\}', '}')
|
113
|
+
.gsub('\\^', '^')
|
114
|
+
.gsub('\\ ', ' ')
|
115
|
+
end
|
116
|
+
|
117
|
+
def extract_tag_names(text, tag_type = :variable)
|
118
|
+
text, regex, extractor =
|
119
|
+
if tag_type == :variable
|
120
|
+
[text, Parser::VARIABLE_MATCHER, ->(match) { "{{%s}}" % match }]
|
121
|
+
else
|
122
|
+
extractor = ->(match) { /#{Regexp.escape("{{%s%s %s %s}}" % match)}/ }
|
123
|
+
tag_type == :full_block ? [text, Parser::BLOCK_MATCHER, extractor] :
|
124
|
+
[text.strip, WHOLE_BLOCK_START_REGEX, extractor]
|
125
|
+
end
|
126
|
+
|
127
|
+
text.scan(regex).map(&extractor)
|
128
|
+
end
|
129
|
+
|
102
130
|
def render_documents(data, text = nil, render_options = {})
|
103
131
|
Hash[
|
104
132
|
@documents.map do |(path, document)|
|
@@ -115,41 +143,48 @@ module LMDocstache
|
|
115
143
|
def problem_paragraphs
|
116
144
|
unusable_tags.flat_map do |tag|
|
117
145
|
@documents.values.inject([]) do |tags, document|
|
118
|
-
faulty_paragraphs = document
|
119
|
-
.
|
120
|
-
|
146
|
+
faulty_paragraphs = document.css('w|p').select do |paragraph|
|
147
|
+
tag_regex = tag.is_a?(Regexp) ? tag : /#{Regexp.escape(tag)}/
|
148
|
+
paragraph.text =~ tag_regex
|
149
|
+
end
|
121
150
|
|
122
151
|
tags + faulty_paragraphs
|
123
152
|
end
|
124
153
|
end
|
125
154
|
end
|
126
155
|
|
127
|
-
def
|
128
|
-
return if (
|
156
|
+
def flatten_text_blocks(runs_wrapper)
|
157
|
+
return if (children = filtered_children(runs_wrapper)).size < 2
|
129
158
|
|
130
|
-
while
|
131
|
-
|
159
|
+
while node = children.pop
|
160
|
+
is_run_node = node.matches?(RUN_LIKE_ELEMENTS)
|
161
|
+
previous_node = children.last
|
132
162
|
|
133
|
-
|
163
|
+
if !is_run_node && filtered_children(node, RUN_LIKE_ELEMENTS).any?
|
164
|
+
next flatten_text_blocks(node)
|
165
|
+
end
|
166
|
+
next if !is_run_node || children.empty? || !previous_node.matches?(RUN_LIKE_ELEMENTS)
|
167
|
+
next if node.at_css('w|tab') || previous_node.at_css('w|tab')
|
168
|
+
|
169
|
+
style_node = node.at_css('w|rPr')
|
134
170
|
style_html = style_node ? style_node.inner_html : ''
|
135
|
-
|
136
|
-
previous_style_node = previous_run_node.at_css('w|rPr')
|
171
|
+
previous_style_node = previous_node.at_css('w|rPr')
|
137
172
|
previous_style_html = previous_style_node ? previous_style_node.inner_html : ''
|
138
|
-
previous_text_node =
|
139
|
-
current_text_node =
|
140
|
-
|
141
|
-
# avoid to merge blocks with tabs
|
142
|
-
next if run_node.at_css('w|tab')
|
143
|
-
next if previous_run_node.at_css('w|tab')
|
173
|
+
previous_text_node = previous_node.at_css('w|t')
|
174
|
+
current_text_node = node.at_css('w|t')
|
144
175
|
|
145
176
|
next if style_html != previous_style_html
|
146
177
|
next if current_text_node.nil? || previous_text_node.nil?
|
147
178
|
|
148
|
-
previous_text_node.content = previous_text_node.text +
|
149
|
-
|
179
|
+
previous_text_node.content = previous_text_node.text + current_text_node.text
|
180
|
+
node.unlink
|
150
181
|
end
|
151
182
|
end
|
152
183
|
|
184
|
+
def filtered_children(node, selector = BLOCK_CHILDREN_ELEMENTS)
|
185
|
+
Nokogiri::XML::NodeSet.new(node.document, node.children.filter(selector))
|
186
|
+
end
|
187
|
+
|
153
188
|
def unzip_read(zip, zip_path)
|
154
189
|
file = zip.find_entry(zip_path)
|
155
190
|
contents = ""
|
data/lib/lm_docstache/parser.rb
CHANGED
@@ -18,7 +18,22 @@ module LMDocstache
|
|
18
18
|
VARIABLE_MATCHER = /{{([^#\^\/].*?)}}/
|
19
19
|
|
20
20
|
attr_reader :document, :data, :blocks, :special_variable_replacements, :hide_custom_tags
|
21
|
+
attr_reader :data_sequential_replacement
|
21
22
|
|
23
|
+
# Constructor +data+ argument is a +Hash+ where the key is
|
24
|
+
# expected to be a +String+ representing the replacement block value. +Hash+
|
25
|
+
# key must not contain the `{{}}` part, but only the pattern characters.
|
26
|
+
# As for the values of the +Hash+, we have options:
|
27
|
+
#
|
28
|
+
# * +String+ will be the value that will replace matching string.
|
29
|
+
# * +Array<String>+ will be an ordered sequence of values that will replace the matched string following
|
30
|
+
# document matching order.
|
31
|
+
#
|
32
|
+
# Example:
|
33
|
+
# { 'full_name' => 'John Doe', 'text|req|Client' => ['John', 'Matt', 'Paul'] }
|
34
|
+
#
|
35
|
+
# Constructor +options+ argument is a +Hash+ where keys can be:
|
36
|
+
#
|
22
37
|
# The +special_variable_replacements+ option is a +Hash+ where the key is
|
23
38
|
# expected to be either a +Regexp+ or a +String+ representing the pattern
|
24
39
|
# of more specific type of variables that deserves a special treatment. The
|
@@ -47,7 +62,8 @@ module LMDocstache
|
|
47
62
|
# will be the value that will replace the matched string
|
48
63
|
def initialize(document, data, options = {})
|
49
64
|
@document = document
|
50
|
-
@data = data.transform_keys(&:to_s)
|
65
|
+
@data = data.transform_keys(&:to_s).select {|e, v| !v.is_a?(Array) }
|
66
|
+
@data_sequential_replacement = data.transform_keys(&:to_s).select {|e, v| v.is_a?(Array) }
|
51
67
|
@special_variable_replacements = add_blocks_to_regexp(options.fetch(:special_variable_replacements, {}))
|
52
68
|
@hide_custom_tags = add_blocks_to_regexp(options.fetch(:hide_custom_tags, {}))
|
53
69
|
end
|
@@ -65,6 +81,7 @@ module LMDocstache
|
|
65
81
|
hide_custom_tags!
|
66
82
|
find_blocks
|
67
83
|
replace_conditional_blocks_in_document!
|
84
|
+
replace_data_sequentially_in_document!
|
68
85
|
replace_variables_in_document!
|
69
86
|
end
|
70
87
|
|
@@ -140,8 +157,35 @@ module LMDocstache
|
|
140
157
|
end
|
141
158
|
end
|
142
159
|
|
160
|
+
def replace_data_sequentially_in_document!
|
161
|
+
data_sequential_replacement.each do |tag_key, values|
|
162
|
+
|
163
|
+
tag = Regexp.escape("{{#{tag_key}}}")
|
164
|
+
pattern_found = 0
|
165
|
+
|
166
|
+
document.css('w|t').each do |text_node|
|
167
|
+
text = text_node.text
|
168
|
+
|
169
|
+
if text.match(tag)
|
170
|
+
|
171
|
+
text.gsub!(/#{tag}/) do |_match|
|
172
|
+
value = values[pattern_found]
|
173
|
+
# if there is no more available value replace the content with empty string
|
174
|
+
return '' unless value
|
175
|
+
|
176
|
+
pattern_found +=1
|
177
|
+
value
|
178
|
+
end
|
179
|
+
|
180
|
+
text_node.content = text
|
181
|
+
end
|
182
|
+
end
|
183
|
+
end
|
184
|
+
end
|
185
|
+
|
143
186
|
def has_skippable_variable?(text)
|
144
|
-
return true if hide_custom_tags.find { |(pattern,
|
187
|
+
return true if hide_custom_tags.find { |(pattern, _)| text =~ pattern }
|
188
|
+
|
145
189
|
!!special_variable_replacements.find do |(pattern, value)|
|
146
190
|
text =~ pattern && value == false
|
147
191
|
end
|
data/lib/lm_docstache/version.rb
CHANGED
Binary file
|
data/spec/integration_spec.rb
CHANGED
@@ -1,5 +1,4 @@
|
|
1
1
|
require 'spec_helper'
|
2
|
-
require 'securerandom'
|
3
2
|
require 'active_support/core_ext/object/blank.rb'
|
4
3
|
|
5
4
|
module LMDocstache
|
@@ -63,7 +62,7 @@ describe 'integration test', integration: true do
|
|
63
62
|
it 'fixes nested xml errors breaking tags' do
|
64
63
|
expect { document.fix_errors }.to change {
|
65
64
|
document.send(:problem_paragraphs).size
|
66
|
-
}.from(
|
65
|
+
}.from(7).to(1)
|
67
66
|
|
68
67
|
expect(document.send(:problem_paragraphs).first.text).to eq(
|
69
68
|
'{{TAG123-\\-//WITH WE👻IRD CHARS}}'
|
@@ -71,7 +70,9 @@ describe 'integration test', integration: true do
|
|
71
70
|
end
|
72
71
|
|
73
72
|
it 'has the expected amount of usable tags' do
|
74
|
-
expect
|
73
|
+
expect { document.fix_errors }.to change {
|
74
|
+
document.usable_tags.count
|
75
|
+
}.from(29).to(34)
|
75
76
|
end
|
76
77
|
|
77
78
|
it 'has the expected amount of usable roles tags' do
|
@@ -80,7 +81,7 @@ describe 'integration test', integration: true do
|
|
80
81
|
end
|
81
82
|
|
82
83
|
it 'has the expected amount of unique tag names' do
|
83
|
-
expect(document.usable_tag_names.count).to eq(
|
84
|
+
expect(document.usable_tag_names.count).to eq(20)
|
84
85
|
end
|
85
86
|
|
86
87
|
it 'renders file using data' do
|
@@ -140,30 +141,5 @@ describe 'integration test', integration: true do
|
|
140
141
|
expect(output).to include('<w:t xml:space="preserve">Test Multiple text in the same line </w:t>')
|
141
142
|
end
|
142
143
|
end
|
143
|
-
|
144
|
-
context "yoooo" do
|
145
|
-
let(:input_file) { "#{base_path}/multi_o.docx" }
|
146
|
-
let(:render_options) {
|
147
|
-
{
|
148
|
-
special_variable_replacements: { "(date|sig|sigfirm|text|check|initial|initials)\\|(req|noreq)\\|(.+?)" => false }.freeze,
|
149
|
-
hide_custom_tags: ['(?:sig|sigfirm|date|check|text|initial)\|(?:req|noreq)\|.+?']
|
150
|
-
}
|
151
|
-
}
|
152
|
-
let(:document) { LMDocstache::Document.new(input_file) }
|
153
|
-
|
154
|
-
it 'should have content replacement aligned with hide custom tags' do
|
155
|
-
doc = document
|
156
|
-
doc.fix_errors
|
157
|
-
new_file_path = "#{Time.now.to_i}-#{SecureRandom.uuid}.docx"
|
158
|
-
n = doc.render_file(new_file_path, { 'full_name' => 'fred document01' }, render_options)
|
159
|
-
noko = doc.render_xml({ 'full_name' => 'fred document01' }, render_options)
|
160
|
-
output = noko['word/document.xml'].to_xml
|
161
|
-
#puts output
|
162
|
-
#doc.render_file(new_file_path, { 'full_name' => 'fred document01' }, render_options)
|
163
|
-
#noko = doc.render_xml({ 'full_name' => 'fred document01' }, render_options)
|
164
|
-
#output = noko['word/document.xml'].to_xml
|
165
|
-
#puts output
|
166
|
-
end
|
167
|
-
end
|
168
144
|
end
|
169
145
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: lm_docstache
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.0.
|
4
|
+
version: 3.0.8
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Roey Chasman
|
@@ -12,7 +12,7 @@ authors:
|
|
12
12
|
autorequire:
|
13
13
|
bindir: bin
|
14
14
|
cert_chain: []
|
15
|
-
date: 2021-
|
15
|
+
date: 2021-06-25 00:00:00.000000000 Z
|
16
16
|
dependencies:
|
17
17
|
- !ruby/object:Gem::Dependency
|
18
18
|
name: nokogiri
|