feat: set our .readalong format to version 1.0 for publication

ReadAlongs · Feb 24, 2023 · 2f0da60 · 2f0da60
1 parent 2e28d86
commit 2f0da60
Show file tree

Hide file tree

Showing 25 changed files with 37 additions and 34 deletions.
diff --git a/docs/cli-guide.rst b/docs/cli-guide.rst
@@ -82,7 +82,7 @@ The format of the generated XML is based on [TEI
 Lite](https://tei-c.org/guidelines/customization/lite/) but is
 considerably simplified.  The DTD (document type definition) can be
 found in the ReadAlong Studio source code under
-`readalongs/static/read-along-0.2.dtd`.
+`readalongs/static/read-along-1.0.dtd`.
 
 .. _dna:
 
@@ -395,7 +395,7 @@ Example:
 .. code-block:: xml
 
    <?xml version='1.0' encoding='utf-8'?>
-   <read-along> <text xml:lang="eng"> <body>
+   <read-along version="1.0"> <text xml:lang="eng"> <body>
        <anchor time="143ms"/>
        <div type="page">
        <p>
@@ -479,7 +479,7 @@ Example:
 .. code-block:: xml
 
    <?xml version='1.0' encoding='utf-8'?>
-   <read-along> <text xml:lang="eng"> <body>
+   <read-along version="1.0"> <text xml:lang="eng"> <body>
        <silence dur="1s"/>
        <div type="page">
        <p>

diff --git a/readalongs/align.py b/readalongs/align.py
@@ -174,7 +174,7 @@ def parse_and_make_xml(
     """Parse XML input and run tokenization and G2P.
 
     Args:
-        xml_path (str): Path to input in ReadAlong XML format (see static/read-along-0.2.dtd)
+        xml_path (str): Path to input in ReadAlong XML format (see static/read-along-1.0.dtd)
         config (dict): Optional; ReadAlong-Studio configuration to use
         save_temps (str): Optional; Save temporary files, by default None
         verbose_g2p_warnings (boolean): Optional; display all g2p errors and warnings
@@ -555,7 +555,7 @@ def align_audio(
     """Align an XML input file to an audio file.
 
     Args:
-        xml_path (str): Path to input file in ReadAlong XML format (see static/read-along-0.2.dtd)
+        xml_path (str): Path to input file in ReadAlong XML format (see static/read-along-1.0.dtd)
         audio_path (str): Path to audio input. Must be in a format supported by ffmpeg
         unit (str): Optional; Element to create alignments for, by default 'w'
         bare (boolean): Optional;
@@ -1105,6 +1105,9 @@ def convert_to_xhtml(tokenized_xml, title="Book"):
         tokenized_xml (etree): xml etree with tokens, converted in place
         title (str, optional): title for xhtml, by default 'Book'
     """
+    # The read-along version ends up as html version, which makes no sense, so remove it
+    if "version" in tokenized_xml.attrib:
+        del tokenized_xml.attrib["version"]
     tokenized_xml.tag = "html"
     tokenized_xml.attrib["xmlns"] = "http://www.w3.org/1999/xhtml"
     for elem in tokenized_xml.iter():
@@ -1131,7 +1134,7 @@ def convert_to_xhtml(tokenized_xml, title="Book"):
 
 
 RAS_TEMPLATE = """<?xml version='1.0' encoding='utf-8'?>
-<read-along version=0.2>
+<read-along version="1.0">
     <text xml:lang="{{main_lang}}" fallback-langs="{{fallback_langs}}">
         <body>
         {{#pages}}
@@ -1152,7 +1155,7 @@ def convert_to_xhtml(tokenized_xml, title="Book"):
 
 
 def create_ras_from_text(lines: Iterable[str], text_languages=Sequence[str]) -> str:
-    """Create input xml in ReadAlong XML format (see static/read-along-0.2.dtd)
+    """Create input xml in ReadAlong XML format (see static/read-along-1.0.dtd)
         Uses the line sequence to infer paragraph and sentence structure from plain text:
         Assumes a double blank line marks a page break, and a single blank line
         marks a paragraph break.
@@ -1198,7 +1201,7 @@ def create_ras_from_text(lines: Iterable[str], text_languages=Sequence[str]) ->
 
 
 def create_input_ras(**kwargs):
-    """Create input xml in ReadAlong XML format (see static/read-along-0.2.dtd)
+    """Create input xml in ReadAlong XML format (see static/read-along-1.0.dtd)
         Uses readlines to infer paragraph and sentence structure from plain text.
         Assumes a double blank line marks a page break, and a single blank line
         marks a paragraph break.

diff --git a/readalongs/static/read-along-0.2.dtd → readalongs/static/read-along-1.0.dtd b/readalongs/static/read-along-0.2.dtd → readalongs/static/read-along-1.0.dtd
@@ -1,4 +1,4 @@
-<!-- VERSION: 0.3 -->
+<!-- VERSION: 1.0 -->
 <!ELEMENT read-along (text|body|div|span|anchor|silence|graphic|p|s|w)*>
 <!ATTLIST read-along
  use-assets-folder CDATA #IMPLIED

diff --git a/readalongs/web_api.py b/readalongs/web_api.py
@@ -77,7 +77,7 @@
 # Call get_langs() when the server loads to load the languages into memory
 LANGS = get_langs()
 # Get the DTD
-DTDPATH = os.path.join(os.path.dirname(__file__), "static", "read-along-0.2.dtd")
+DTDPATH = os.path.join(os.path.dirname(__file__), "static", "read-along-1.0.dtd")
 with open(DTDPATH) as dtdfh:
     DTD = etree.DTD(dtdfh)
 
@@ -161,7 +161,7 @@ async def assemble(
             "xml": {
                 "summary": "A basic example with xml input",
                 "value": {
-                    "input": "<?xml version='1.0' encoding='utf-8'?><read-along><text><p><s>hej verden</s></p></text></read-along>",
+                    "input": "<?xml version='1.0' encoding='utf-8'?><read-along version=\"1.0\"><text><p><s>hej verden</s></p></text></read-along>",
                     "type": "application/readalong+xml",
                     "text_languages": ["dan", "und"],
                     "debug": False,
@@ -321,7 +321,7 @@ class ConvertRequest(BaseModel):
         example=dedent(
             """\
             <?xml version='1.0' encoding='utf-8'?>
-            <read-along>
+            <read-along version="1.0">
                 <text xml:lang="dan" fallback-langs="und" id="t0">
                     <body id="t0b0">
                         <div type="page" id="t0b0d0">

diff --git a/test/data/ej-fra-anchors.readalong b/test/data/ej-fra-anchors.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/ej-fra-anchors2.readalong b/test/data/ej-fra-anchors2.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <anchor time=".5s"/>
         <body>

diff --git a/test/data/ej-fra-converted.readalong b/test/data/ej-fra-converted.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra" id="t0">
         <body id="t0b0">
             <div type="page" id="t0b0d0">

diff --git a/test/data/ej-fra-dna.readalong b/test/data/ej-fra-dna.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/ej-fra-invalid.readalong b/test/data/ej-fra-invalid.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
   <!-- Note the typo: this should fail validation -->
     <txet xml:lang="fra">
         <body>

diff --git a/test/data/ej-fra-package.readalong b/test/data/ej-fra-package.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/ej-fra-silence-bad.readalong b/test/data/ej-fra-silence-bad.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/ej-fra-silence.readalong b/test/data/ej-fra-silence.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/ej-fra-subword.readalong b/test/data/ej-fra-subword.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <!-- To exclude any element from alignment, add the do-not-align="true" attribute to
          it, e.g., <p do-not-align="true">...</p>, or
          <s>Some text <foo do-not-align="true">do not align this</foo> more text</s> -->

diff --git a/test/data/ej-fra-translated.readalong b/test/data/ej-fra-translated.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <!-- To exclude any element from alignment, add the do-not-align="true" attribute to
          it, e.g., <p do-not-align="true">...</p>, or
          <s>Some text <foo do-not-align="true">do not align this</foo> more text</s> -->

diff --git a/test/data/ej-fra.readalong b/test/data/ej-fra.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/fra-prepared.readalong b/test/data/fra-prepared.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra" fallback-langs="und">
         <body>
             <div type="page">

diff --git a/test/data/fra-tokenized.readalong b/test/data/fra-tokenized.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text xml:lang="fra">
         <body>
             <div type="page">

diff --git a/test/data/mixed-langs.g2p.readalong b/test/data/mixed-langs.g2p.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text id="t0">
         <body id="t0b0">
             <div type="page" id="t0b0d0">

diff --git a/test/data/mixed-langs.readalong b/test/data/mixed-langs.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text>
         <body>
             <div type="page">

diff --git a/test/data/mixed-langs.tokenized.readalong b/test/data/mixed-langs.tokenized.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
     <text>
         <body>
             <div type="page">

diff --git a/test/data/patrickxtlan.readalong b/test/data/patrickxtlan.readalong
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<read-along>
+<read-along version="1.0">
   <text>
     <body>
     <p>

diff --git a/test/test_align_cli.py b/test/test_align_cli.py
@@ -303,7 +303,7 @@ def test_bad_anchors(self):
         """Make sure invalid anchors yield appropriate errors"""
 
         xml_text = """<?xml version='1.0' encoding='utf-8'?>
-            <read-along><text xml:lang="fra"><body><p>
+            <read-along version="1.0"><text xml:lang="fra"><body><p>
             <anchor /><s>Bonjour.</s><anchor time="invalid"/>
             </p></body></text></read-along>
         """

diff --git a/test/test_dtd.py b/test/test_dtd.py
@@ -9,7 +9,7 @@
 from lxml import etree
 
 DTDPATH = os.path.join(
-    dirname(__file__), "..", "readalongs", "static", "read-along-0.2.dtd"
+    dirname(__file__), "..", "readalongs", "static", "read-along-1.0.dtd"
 )
 
 VALID_RAS = """

diff --git a/test/test_misc.py b/test/test_misc.py
@@ -88,7 +88,7 @@ def test_split_silences(self):
         self.assertEqual(words, ref)
 
     def test_get_attrib_recursive(self):
-        raw_xml = """<read-along>
+        raw_xml = """<read-along version="1.0">
             <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>

diff --git a/test/test_web_api.py b/test/test_web_api.py
@@ -165,7 +165,7 @@ def test_debug(self):
     hej_verden_xml = dedent(
         """\
         <?xml version='1.0' encoding='utf-8'?>
-        <read-along>
+        <read-along version="1.0">
             <text xml:lang="dan" fallback-langs="und" id="t0">
                 <body id="t0b0">
                     <div type="page" id="t0b0d0">
@@ -390,7 +390,7 @@ def test_cleanup_even_if_error(self):
         overlap_xml = dedent(
             """\
         <?xml version='1.0' encoding='utf-8'?>
-        <read-along>
+        <read-along version="1.0">
             <text xml:lang="dan" fallback-langs="und" id="t0">
                 <body id="t0b0">
                     <div type="page" id="t0b0d0">