duplicated examples, fixed xlink namespace

GALAglobal · Jan 24, 2018 · 0abc8e6 · 0abc8e6
1 parent 9a01f2f
commit 0abc8e6
Show file tree

Hide file tree

Showing 129 changed files with 2,434 additions and 70 deletions.
diff --git a/docbook/T1/WG3/XLIFF-EM-BP.xml b/docbook/T1/WG3/XLIFF-EM-BP.xml
@@ -212,13 +212,13 @@
           code. In HTML that can be <code>&lt;bold>text&lt;/bold></code>, in RTF <code>\b text
             \b0</code>.</para>
         <para>In XLIFF2 such code can be represented using <code><link
-              xlink:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#sc"
-              xmlns:xlink="http://www.w3.org/1999/xlink">&lt;sc /></link></code>/<code><link
-              xlink:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#ec"
-              xmlns:xlink="http://www.w3.org/1999/xlink">&lt;ec /></link></code> pair universally,
+              xl:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#sc"
+              >&lt;sc /></link></code>/<code><link
+              xl:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#ec"
+              >&lt;ec /></link></code> pair universally,
           or by <code><link
-              xlink:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#pc"
-              xmlns:xlink="http://www.w3.org/1999/xlink">&lt;pc>&lt;/pc></link></code> in case of
+              xl:href="http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#pc"
+              >&lt;pc>&lt;/pc></link></code> in case of
           well formed spanning code.</para>
         <para>Ideally the original format is documented enough to instruct Extractor about role of
           each inline code. For example XML schema allows to declare elements using keyword EMPTY.

diff --git a/docs/T1/WG3/XLIFF-EM-BP-ED.html b/docs/T1/WG3/XLIFF-EM-BP-ED.html
diff --git a/docs/T1/WG3/XLIFF-EM-BP-ED.pdf b/docs/T1/WG3/XLIFF-EM-BP-ED.pdf
diff --git a/docs/T1/WG3/extraction_examples/README.md b/docs/T1/WG3/extraction_examples/README.md
@@ -0,0 +1,6 @@
+Extraction (and merging) best practices
+===
+
+Repository of different approaches for extracting localizable content into XLIFF2.
+
+New samples and feedback on existing ones via [pull request](https://help.github.com/articles/about-pull-requests/) or via [commit comments](https://github.com/blog/42-commit-comments) is welcomed.
diff --git a/docs/T1/WG3/extraction_examples/cdata/bad.xlf b/docs/T1/WG3/extraction_examples/cdata/bad.xlf
@@ -0,0 +1,19 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source><![CDATA[<b>bold</b> text]]></source>
+                <target><![CDATA[text <b>tučným</b>]]></target>
+                <!-- inline content does not enjoy benefits of proper extraction,
+                    such as correct representation in CAT tool and protection during
+                    the round-trip. It's not possible to use native XLIFF validation
+                    artifacts-->
+                <!-- It's legal for Modifier to change CDATA into normal escaped content.
+                     Merger  has to be able to accept such change
+                -->
+                <!-- http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#d0e8112 (4.4 CDATA sections)-->
+                <!-- https://www.w3.org/TR/xml-i18n-bp/#AuthCDATA -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/cdata/good.xlf b/docs/T1/WG3/extraction_examples/cdata/good.xlf
@@ -0,0 +1,10 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source><pc id="1">bold</pc> text</source>
+                <target>text <pc id="1">tučným</pc></target>
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/cdata/source.html b/docs/T1/WG3/extraction_examples/cdata/source.html
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head></head>
+    <body>bold <b>text</b></body>
+</html>
diff --git a/docs/T1/WG3/extraction_examples/context_hints/bad.xlf b/docs/T1/WG3/extraction_examples/context_hints/bad.xlf
@@ -0,0 +1,17 @@
+<xliff version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0" srcLang="en-US">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source>a link</source>
+            </segment>
+        </unit>
+        <unit id="u2">
+            <segment>
+                <source>A text with <pc id="1">hyperlink</pc>, <pc id="2">italics</pc> and some
+                    <ph id="3"/></source>
+                <!-- No additional context is provided to translator, which could impact the
+                    quality of translation. Role of the inline tags is unknown.-->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/context_hints/good.xlf b/docs/T1/WG3/extraction_examples/context_hints/good.xlf
@@ -0,0 +1,29 @@
+<xliff version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0" srcLang="en-US">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source>a link</source>
+            </segment>
+        </unit>
+        <unit id="u2">
+            <segment>
+                <!-- newlines added for readability -->
+                <source>A text with 
+                    <sc id="1"
+                        disp="&lt;a>" 
+                        equiv="[www.example.com]"
+                        type="link" subFlows="u1" />
+                            hyperlink
+                    <ec disp="&lt;/a>" startRef="1"/>, 
+                    <sc id="2"
+                        disp="&lt;i>" 
+                        type="fmt" subType="xlf:i" />
+                            italics
+                    <ec disp="&lt;/i>" startRef="2"/>
+                    and some
+                    <ph id="3" disp="{placeholder}" equiv="[user name]" type="ui" subType="xlf:var"/></source>
+                <!-- plethora of context hints helps translator to make accurate judgement -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/context_hints/source.html b/docs/T1/WG3/extraction_examples/context_hints/source.html
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head>
+        <title></title>
+    </head>
+    <body>A text with <a href="www.example.com" title="a link">hyperlink</a>, <i>italics</i> and some {placeholder}</body>
+</html>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canDelete/bad.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canDelete/bad.xlf
@@ -0,0 +1,11 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source>irrelevant <pc id="1">bold</pc> text and important <pc id="2">hyperlink</pc>, also a critical <ph id="3"/></source>
+                <target>nepodstatný <pc id="1">tučný</pc>text a dôležity hyperlink, tiež </target>
+                <!-- missing editing hints do not allow to distinguish between important and irrelevant inline codes, preventing native validation -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canDelete/good.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canDelete/good.xlf
@@ -0,0 +1,14 @@
+<xliff version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0" srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source>irrelevant <pc canCopy="no" canDelete="yes" id="1">bold</pc> text and
+                    important <pc canCopy="no" canDelete="no" id="2">hyperlink</pc>, also a critical
+                        <ph canCopy="no" canDelete="no" id="3"/></source>
+                <target>nepodstatný tučný text a dôležity <pc canCopy="no" canDelete="no" id="2"
+                        >hyperlink</pc>, tiež <ph canCopy="no" canDelete="no" id="3"/></target>
+                <!-- canDelete is "yes" by default, thus can be committed. for pc id=1 included for clarity -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canDelete/source.html b/docs/T1/WG3/extraction_examples/editing_hints_canDelete/source.html
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head>
+        <title></title>
+    </head>
+    <body>irrelevant <b>bold</b> and important <a>hyperlink text</a>, also a critical {placeholder}</body>
+</html>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/Invalid_bad.xhtml b/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/Invalid_bad.xhtml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head>
+        <title></title>
+    </head>
+    <body>
+        <b>tučné<i></b> a kurzíva</i>
+        <!-- malformed inline formatting tags -->
+    </body>
+</html>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/bad.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/bad.xlf
@@ -0,0 +1,21 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <!-- whitespace added for readability -->
+            <segment>
+                <source><sc id="1" equiv="b"/>
+                    bold
+                    <ec startRef="1" equiv="/b"/> 
+                    and 
+                    <sc id="2" equiv="i"/>
+                    italic
+                    <ec startRef="2" equiv="/i"/></source>
+                <target><sc id="1" equiv="b"/> <!-- opening bold -->
+                    tučné<sc id="2" equiv="i"/> <!-- opening italic -->
+                    <ec startRef="1" equiv="/b"/> <!-- closing bold -->
+                    a kurzíva
+                    <ec startRef="2" equiv="/i"/></target> <!-- closing italic -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/good.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/good.xlf
@@ -0,0 +1,26 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <!-- whitespace added for readability -->
+            <segment>
+                <source xml:space="preserve"><sc id="1" equiv="b" canOverlap="no"/>
+                    bold
+                    <ec startRef="1" equiv="/b" canOverlap="no"/> 
+                    and 
+                    <sc id="2" equiv="i" canOverlap="no" />
+                    italic
+                    <ec startRef="2" equiv="/i" canOverlap="no" /></source>
+                <target><sc id="1" equiv="b"/>
+                    tučné
+                    <ec startRef="1" equiv="/b" />
+                    a
+                    <sc id="2" equiv="i" />
+                    kurzíva
+                    <ec startRef="2" equiv="/i" /></target>
+                <!-- native XLIFF validation can detect overlapping
+                    with canOverlap="yes"
+                -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/source.xhtml b/docs/T1/WG3/extraction_examples/editing_hints_canOverlap/source.xhtml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+    <head>
+        <title></title>
+    </head>
+    <body>
+        <b>bold</b> and <i>italic</i>
+        <!-- well-formed inline formatting tags -->
+    </body>
+</html>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canReorder/bad.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canReorder/bad.xlf
@@ -0,0 +1,19 @@
+<xliff version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0" srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <!-- newlines added for readability -->
+                <source><pc id="1"> <!-- link -->
+                        <pc id="2">this is linktext</pc> <!-- title -->
+                        <ph id="3"/> <!-- URI -->
+                    </pc></source>
+
+                <target><pc id="1"></pc> <!-- link is empty -->
+                    <pc id="2">toto je linktext
+                        <ph id="3"/> <!-- URI is child of title -->
+                    </pc></target>
+                <!-- missing canReorder prevents target validation -->
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canReorder/bad_target.xml b/docs/T1/WG3/extraction_examples/editing_hints_canReorder/bad_target.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<root>
+    <link />
+    <!-- empty link -->
+    <title>this is linktext <uri>http://example.com</uri>
+        <!-- URI as a child of title -->
+    </title>
+</root>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canReorder/good.xlf b/docs/T1/WG3/extraction_examples/editing_hints_canReorder/good.xlf
@@ -0,0 +1,17 @@
+<xliff version='2.0' xmlns='urn:oasis:names:tc:xliff:document:2.0' srcLang="en-US" trgLang="sk-SK">
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <!-- newlines added for readability -->
+                <source><pc id="1" canCopy="no" canDelete="no" canReorder="firstNo">
+                        <pc id="2" canCopy="no" canDelete="no" canReorder="no">this is linktext</pc>
+                        <ph id="3" canCopy="no" canDelete="no" canReorder="no"/>
+                    </pc></source>
+                <target><pc id="1" canCopy="no" canDelete="no" canReorder="firstNo">
+                        <pc id="2" canCopy="no" canDelete="no" canReorder="no">toto je linktext</pc>
+                        <ph id="3" canCopy="no" canDelete="no" canReorder="no"/>
+                    </pc></target>
+            </segment>
+        </unit>
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/editing_hints_canReorder/source.xml b/docs/T1/WG3/extraction_examples/editing_hints_canReorder/source.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<root>
+    <link>
+        <title>this is linktext</title>
+        <uri>http://example.com</uri>
+    </link>
+    <!-- <title> and <uri> are children of <link> with specified order -->
+</root>
diff --git a/docs/T1/WG3/extraction_examples/group/bad.xlf b/docs/T1/WG3/extraction_examples/group/bad.xlf
@@ -0,0 +1,35 @@
+<xliff version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0" srcLang="en-US" >
+    <file id="f1">
+        <unit id="u1">
+            <segment>
+                <source>First paragraph</source>
+            </segment>
+        </unit>
+        <unit id="u2">
+            <segment>
+                <source>Second paragraph</source>
+            </segment>
+        </unit>
+        <unit id="u4">
+            <segment>
+                <source>Firstname</source>
+            </segment>
+        </unit>
+        <unit id="u5">
+            <segment>
+                <source>Lastname</source>
+            </segment>
+        </unit>
+        <unit id="u6">
+            <segment>
+                <source>Age</source>
+            </segment>
+        </unit>
+        <!-- Flat XLIFF structure does not provide additional context information
+            possibly impairing the quality of the translation. Group can contain <notes>
+            and has an extension point for elements from MDA, SLR, VAL and ITS modules
+            and FS module attributes, thus narrowing the scope of the information
+            contained in them.
+        -->
+    </file>
+</xliff>
diff --git a/docs/T1/WG3/extraction_examples/group/good.xlf b/docs/T1/WG3/extraction_examples/group/good.xlf
@@ -0,0 +1,51 @@
+<xliff srcLang="en-US" version="2.0" xmlns="urn:oasis:names:tc:xliff:document:2.0">
+    <file id="f1">
+        <group id="g1" name="main">
+            <!-- This group corresponds to div in the source doc. 
+                Units map to paragraphs. -->
+            <unit id="u1">
+                <segment>
+                    <source>First paragraph</source>
+                </segment>
+            </unit>
+            <unit id="u2">
+                <segment>
+                    <source>Second paragraph</source>
+                </segment>
+            </unit>
+        </group>
+        <group id="g2" name="table1">
+            <!-- Group corresponds to whole table -->
+            <group id="g2_1">
+                <!-- Nested group corresponds to table header.
+                    Value of @id is arbitrary NMTOKEN and depends on Extractor. 
+                    Units are table cells. Suitable approach if cells need additional
+                    segmentation
+                -->
+                <unit id="u4">
+                    <segment>
+                        <source>Firstname</source>
+                    </segment>
+                </unit>
+                <unit id="u5">
+                    <segment>
+                        <source>Lastname</source>
+                    </segment>
+                </unit>
+                <unit id="u6">
+                    <segment>
+                        <source>Age</source>
+                    </segment>
+                </unit>
+            </group>
+            <!-- Each additional table row would create new group -->
+            <!-- Comparable approach would be to use <unit> for table row 
+                with canResegment="no", where each segment would represent
+                a cell. This approach is suitable for short cell text.
+            -->
+        </group>
+        <!-- Focus is on XLIFF core features. In this case it would be particularly suitable to use
+            Format Style Module for additional context and to help render the preview. 
+            http://docs.oasis-open.org/xliff/xliff-core/v2.1/xliff-core-v2.1.html#fs-mod -->
+    </file>
+</xliff>