feat: refine the DTD somewhat

- add a version number in comment and filename - set the root element to `<read-along>` and add attributes from web component - allow things in a lot more places - add `<span>`
ReadAlongs · Feb 8, 2023 · b7285f5 · b7285f5
1 parent 899dbf3
commit b7285f5
Show file tree

Hide file tree

Showing 18 changed files with 67 additions and 42 deletions.
diff --git a/readalongs/align.py b/readalongs/align.py
@@ -1141,7 +1141,7 @@ def convert_to_xhtml(tokenized_xml, title="Book"):
 
 
 RAS_TEMPLATE = """<?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="{{main_lang}}" fallback-langs="{{fallback_langs}}">
         <body>
         {{#pages}}
@@ -1157,7 +1157,7 @@ def convert_to_xhtml(tokenized_xml, title="Book"):
         {{/pages}}
         </body>
     </text>
-</readalong>
+</read-along>
 """
 
 

diff --git a/readalongs/static/readalong.dtd → readalongs/static/read-along-0.1.dtd b/readalongs/static/readalong.dtd → readalongs/static/read-along-0.1.dtd
@@ -1,14 +1,24 @@
-<!ELEMENT readalong (text)>
-<!ELEMENT text (body|anchor)*>
+<!-- VERSION: 0.1 -->
+<!ELEMENT read-along (text|body|div|span|anchor|silence|graphic|p|s|w)*>
+<!ATTLIST read-along
+ use-assets-folder CDATA #IMPLIED
+ href CDATA #IMPLIED
+ audio CDATA #IMPLIED
+ xml:lang CDATA #IMPLIED
+ language CDATA #IMPLIED
+ lang CDATA #IMPLIED>
+
+<!ELEMENT text (body|div|span|anchor|silence|graphic|p|s|w)*>
 <!ATTLIST text
  xml:lang CDATA #IMPLIED
  lang CDATA #IMPLIED
  fallback-langs CDATA #IMPLIED
  id CDATA #IMPLIED>
 
-<!ELEMENT body (div|anchor|silence|graphic|p|s|w)*>
+<!ELEMENT body (div|span|anchor|silence|graphic|p|s|w)*>
 <!ATTLIST body
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED>
 
 <!ELEMENT anchor EMPTY>
@@ -22,44 +32,59 @@
  url CDATA #REQUIRED
  id CDATA #IMPLIED>
 
-<!ELEMENT div (#PCDATA|anchor|silence|graphic|p|s|w)*>
+<!ELEMENT div (#PCDATA|div|span|anchor|silence|graphic|p|s|w)*>
 <!ATTLIST div
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
+ id CDATA #IMPLIED
+ type CDATA #IMPLIED
+ do-not-align CDATA #IMPLIED
+ time CDATA #IMPLIED
+ dur CDATA #IMPLIED>
+
+<!ELEMENT span (#PCDATA|div|span|anchor|silence|graphic|p|s|w)*>
+<!ATTLIST span
+ xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED
  type CDATA #IMPLIED
  do-not-align CDATA #IMPLIED
  time CDATA #IMPLIED
  dur CDATA #IMPLIED>
 
-<!ELEMENT p (#PCDATA|anchor|silence|s|w)*>
+<!ELEMENT p (#PCDATA|span|anchor|silence|s|w)*>
 <!ATTLIST p
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED
  do-not-align CDATA #IMPLIED
  time CDATA #IMPLIED
  dur CDATA #IMPLIED>
 
-<!ELEMENT s (#PCDATA|anchor|silence|w)*>
+<!ELEMENT s (#PCDATA|span|anchor|silence|w)*>
 <!ATTLIST s
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED
  class CDATA #IMPLIED
  do-not-align CDATA #IMPLIED
  time CDATA #IMPLIED
  dur CDATA #IMPLIED>
 
-<!ELEMENT w (#PCDATA|syl)*>
+<!ELEMENT w (#PCDATA|span|syl)*>
 <!ATTLIST w
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED
  do-not-align CDATA #IMPLIED
  ARPABET CDATA #IMPLIED
  time CDATA #IMPLIED
  dur CDATA #IMPLIED>
 
-<!ELEMENT syl (#PCDATA)>
+<!ELEMENT syl (#PCDATA|span)*>
 <!ATTLIST syl
  xml:lang CDATA #IMPLIED
+ lang CDATA #IMPLIED
  id CDATA #IMPLIED
  do-not-align CDATA #IMPLIED
  ARPABET CDATA #IMPLIED

diff --git a/test/data/ej-fra-anchors.xml b/test/data/ej-fra-anchors.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -23,4 +23,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-anchors2.xml b/test/data/ej-fra-anchors2.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <anchor time=".5s"/>
         <body>
@@ -25,4 +25,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-converted.xml b/test/data/ej-fra-converted.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra" id="t0">
         <body id="t0b0">
             <div type="page" id="t0b0d0">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-dna.xml b/test/data/ej-fra-dna.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -28,4 +28,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-package.xml b/test/data/ej-fra-package.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -23,4 +23,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-silence-bad.xml b/test/data/ej-fra-silence-bad.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra-silence.xml b/test/data/ej-fra-silence.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/ej-fra.xml b/test/data/ej-fra.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/fra-prepared.xml b/test/data/fra-prepared.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra" fallback-langs="und">
         <body>
             <div type="page">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/fra-tokenized.xml b/test/data/fra-tokenized.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text xml:lang="fra">
         <body>
             <div type="page">
@@ -21,4 +21,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/mixed-langs.g2p.xml b/test/data/mixed-langs.g2p.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text id="t0">
         <body id="t0b0">
             <div type="page" id="t0b0d0">
@@ -12,4 +12,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/mixed-langs.tokenized.xml b/test/data/mixed-langs.tokenized.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text>
         <body>
             <div type="page">
@@ -12,4 +12,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/mixed-langs.xml b/test/data/mixed-langs.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
     <text>
         <body>
             <div type="page">
@@ -12,4 +12,4 @@
             </div>
         </body>
     </text>
-</readalong>
+</read-along>
diff --git a/test/data/patrickxtlan.xml b/test/data/patrickxtlan.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<readalong>
+<read-along>
   <text>
     <body>
     <p>
@@ -9,4 +9,4 @@
     </p>
     </body>
   </text>
-</readalong>
+</read-along>
diff --git a/test/test_align_cli.py b/test/test_align_cli.py
@@ -313,9 +313,9 @@ def test_bad_anchors(self):
         """Make sure invalid anchors yield appropriate errors"""
 
         xml_text = """<?xml version='1.0' encoding='utf-8'?>
-            <readalong><text xml:lang="fra"><body><p>
+            <read-along><text xml:lang="fra"><body><p>
             <anchor /><s>Bonjour.</s><anchor time="invalid"/>
-            </p></body></text></readalong>
+            </p></body></text></read-along>
         """
         xml_file = join(self.tempdir, "bad-anchor.xml")
         with open(xml_file, "w", encoding="utf8") as f:

diff --git a/test/test_misc.py b/test/test_misc.py
@@ -86,7 +86,7 @@ def test_split_silences(self):
         self.assertEqual(words, ref)
 
     def test_get_attrib_recursive(self):
-        raw_xml = """<readalong>
+        raw_xml = """<read-along>
             <text lang="text">
             <p lang="p1"><s>stuff</s><s lang="p1s2">nonsense</s></p>
             <p><s lang="p2s1">stuff</s><s>nonsense</s></p>
@@ -97,7 +97,7 @@ def test_get_attrib_recursive(self):
             <text>
             <p><s xml:lang="p4s1" lang="not:xml:lang">stuff</s><s>nonsense<s xml:lang="p4p2c">!</s></s></p>
             </text>
-            </readalong>
+            </read-along>
         """
         xml = etree.fromstring(raw_xml)
         for i, s, lang in zip(