canon 0.3.0 → 0.3.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/canon/version.rb +1 -1
- data/lib/canon/xml/data_model.rb +29 -40
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b000e9e89684d66d4f037a950a2121a88717dd6c72d975648742f32b5a83fb9f
|
|
4
|
+
data.tar.gz: c5e8b5ecfdcb8435559be3e6c940e8e8bec99202054b90fa857f9e3afd3097e2
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: '0804e7a2a07ff2687e363ee2bd0a1e2d00a5fe826e45ae5bd69fe26749bf2e2b1517a6fb2fcd3518e41d7d9bf6bf0b76fd8e704c288293724d27cbc3613978f4'
|
|
7
|
+
data.tar.gz: 6d9dca5aa3c29bbde5d067ca02e2a22c4d7bee098635e0fd8b48df16fbf08102fa713608f1965d198f3ace1c064743916b57d34d7a2cc2a6b845902e1553a045
|
data/lib/canon/version.rb
CHANGED
data/lib/canon/xml/data_model.rb
CHANGED
|
@@ -154,11 +154,12 @@ module Canon
|
|
|
154
154
|
end
|
|
155
155
|
|
|
156
156
|
def self.build_node_from_nokogiri(nokogiri_node,
|
|
157
|
-
preserve_whitespace: false)
|
|
157
|
+
preserve_whitespace: false, inherited_namespaces: nil)
|
|
158
158
|
case nokogiri_node
|
|
159
159
|
when Nokogiri::XML::Element
|
|
160
160
|
build_element_node(nokogiri_node,
|
|
161
|
-
preserve_whitespace: preserve_whitespace
|
|
161
|
+
preserve_whitespace: preserve_whitespace,
|
|
162
|
+
inherited_namespaces: inherited_namespaces)
|
|
162
163
|
when Nokogiri::XML::Text, Nokogiri::XML::CDATA
|
|
163
164
|
build_text_node(nokogiri_node,
|
|
164
165
|
preserve_whitespace: preserve_whitespace)
|
|
@@ -169,56 +170,44 @@ preserve_whitespace: false)
|
|
|
169
170
|
end
|
|
170
171
|
end
|
|
171
172
|
|
|
172
|
-
def self.build_element_node(nokogiri_element, preserve_whitespace: false
|
|
173
|
+
def self.build_element_node(nokogiri_element, preserve_whitespace: false,
|
|
174
|
+
inherited_namespaces: nil)
|
|
173
175
|
element = Nodes::ElementNode.new(
|
|
174
176
|
name: nokogiri_element.name,
|
|
175
177
|
namespace_uri: nokogiri_element.namespace&.href,
|
|
176
178
|
prefix: nokogiri_element.namespace&.prefix,
|
|
177
179
|
)
|
|
178
180
|
|
|
179
|
-
|
|
181
|
+
scope = nokogiri_namespace_scope(nokogiri_element, inherited_namespaces)
|
|
182
|
+
scope.each do |prefix, uri|
|
|
183
|
+
element.add_namespace(Nodes::NamespaceNode.new(
|
|
184
|
+
prefix: prefix,
|
|
185
|
+
uri: uri,
|
|
186
|
+
))
|
|
187
|
+
end
|
|
188
|
+
|
|
180
189
|
build_attribute_nodes(nokogiri_element, element)
|
|
181
190
|
|
|
182
191
|
nokogiri_element.children.each do |child|
|
|
183
192
|
node = build_node_from_nokogiri(child,
|
|
184
|
-
preserve_whitespace: preserve_whitespace
|
|
193
|
+
preserve_whitespace: preserve_whitespace,
|
|
194
|
+
inherited_namespaces: scope)
|
|
185
195
|
element.add_child(node) if node
|
|
186
196
|
end
|
|
187
197
|
|
|
188
198
|
element
|
|
189
199
|
end
|
|
190
200
|
|
|
191
|
-
|
|
192
|
-
|
|
193
|
-
|
|
194
|
-
|
|
195
|
-
|
|
196
|
-
|
|
197
|
-
|
|
198
|
-
|
|
199
|
-
element.add_namespace(ns_node)
|
|
200
|
-
end
|
|
201
|
-
end
|
|
202
|
-
|
|
203
|
-
def self.collect_in_scope_namespaces(nokogiri_element)
|
|
204
|
-
namespaces = {}
|
|
205
|
-
|
|
206
|
-
current = nokogiri_element
|
|
207
|
-
while current && !current.is_a?(Nokogiri::XML::Document)
|
|
208
|
-
if current.is_a?(Nokogiri::XML::Element)
|
|
209
|
-
current.namespace_definitions.each do |ns|
|
|
210
|
-
prefix = ns.prefix || ""
|
|
211
|
-
unless namespaces.key?(prefix)
|
|
212
|
-
namespaces[prefix] = ns.href
|
|
213
|
-
end
|
|
214
|
-
end
|
|
215
|
-
end
|
|
216
|
-
current = current.parent
|
|
201
|
+
# In-scope namespace bindings: the element's own declarations
|
|
202
|
+
# shadow inherited ones, xml is prebound. The scope is passed down
|
|
203
|
+
# the recursion — one definition fetch per element instead of an
|
|
204
|
+
# ancestor walk per element (O(n) total, not O(n * depth)).
|
|
205
|
+
def self.nokogiri_namespace_scope(nokogiri_element, inherited)
|
|
206
|
+
scope = inherited ? inherited.dup : { "xml" => "http://www.w3.org/XML/1998/namespace" }
|
|
207
|
+
nokogiri_element.namespace_definitions.each do |ns|
|
|
208
|
+
scope[ns.prefix || ""] = ns.href
|
|
217
209
|
end
|
|
218
|
-
|
|
219
|
-
namespaces["xml"] ||= "http://www.w3.org/XML/1998/namespace"
|
|
220
|
-
|
|
221
|
-
namespaces
|
|
210
|
+
scope
|
|
222
211
|
end
|
|
223
212
|
|
|
224
213
|
def self.build_attribute_nodes(nokogiri_element, element)
|
|
@@ -261,7 +250,7 @@ preserve_whitespace: false)
|
|
|
261
250
|
# --- Moxml path ---
|
|
262
251
|
|
|
263
252
|
def self.from_moxml_xml(xml_string, preserve_whitespace:)
|
|
264
|
-
doc = Canon::XmlParsing.parse(xml_string)
|
|
253
|
+
doc = Canon::XmlParsing.moxml_context.parse(xml_string, readonly: true)
|
|
265
254
|
check_moxml_relative_namespace_uris(doc)
|
|
266
255
|
result = build_from_moxml(doc, preserve_whitespace: preserve_whitespace)
|
|
267
256
|
# Canon owns this document's full lifecycle: the canon tree holds
|
|
@@ -390,11 +379,11 @@ preserve_whitespace: false)
|
|
|
390
379
|
))
|
|
391
380
|
end
|
|
392
381
|
|
|
393
|
-
# Adopt completed children
|
|
394
|
-
#
|
|
382
|
+
# Adopt completed children: they pop in reverse order; reversing
|
|
383
|
+
# once is O(n) (unshift per child would be O(n^2) on wide trees).
|
|
395
384
|
children = []
|
|
396
|
-
children
|
|
397
|
-
children.
|
|
385
|
+
children << frames.pop[1] while frames.any? && frames.last[0] > record[:depth]
|
|
386
|
+
children.reverse_each { |child| element.add_child(child) }
|
|
398
387
|
|
|
399
388
|
own_namespaces[element] = record[:namespaces]
|
|
400
389
|
element
|