speechmarkdown-rust 0.4.8__tar.gz → 0.4.10__tar.gz

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "speechmarkdown-rust"
-version = "0.4.8"
+version = "0.4.10"
 edition = "2021"
 authors = ["SpeechMarkdown Contributors"]
 description = "High-performance SpeechMarkdown parser with multi-language bindings"
@@ -15,6 +15,11 @@ quick-xml = "0.37"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 thiserror = "1.0"
+ipa-translate = { version = "0.2", optional = true }
+
+[features]
+default = ["phonetic-translation"]
+phonetic-translation = ["dep:ipa-translate"]
 
 [dev-dependencies]
 # Removed problematic benchmark dependencies for now

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: speechmarkdown-rust
-Version: 0.4.8
+Version: 0.4.10
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Multimedia :: Sound/Audio :: Speech

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/Package.swift

@@ -10,8 +10,8 @@ let package = Package(
     targets: [
         .binaryTarget(
             name: "SpeechMarkdownRust",
-            url: "https://github.com/AACTools/speechmarkdown-rust/releases/download/v0.4.7/SpeechMarkdownRust.xcframework.zip",
-            checksum: "4fd89b1def83868e4b540430c0d09642402e722dca0e0c36e7d2e49814663f23"
+            url: "https://github.com/AACTools/speechmarkdown-rust/releases/download/v0.4.9/SpeechMarkdownRust.xcframework.zip",
+            checksum: "98955acaaa84a2893e7cb6d81f404dc426b5b926be33ebc286a46f766ff2a5c9"
         ),
         .target(
             name: "CSpeechMarkdown",

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/bindings/dotnet/SpeechMarkdown.nuspec

@@ -2,7 +2,7 @@
 <package>
   <metadata>
     <id>SpeechMarkdown</id>
-    <version>0.4.8</version>
+    <version>0.4.10</version>
     <title>SpeechMarkdown</title>
     <authors>SpeechMarkdown Contributors</authors>
     <description>SpeechMarkdown parser - convert SpeechMarkdown syntax to SSML for Alexa, Google Assistant, Azure, and more.</description>

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/bindings/python/Cargo.lock

@@ -29,12 +29,27 @@ dependencies = [
  "rustversion",
 ]
 
+[[package]]
+name = "ipa-translate"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c470a66e67f5e334a68a4a4e199b3926fad0a77bc91c663e9ef4a6be4dc68bd"
+dependencies = [
+ "lazy_static",
+]
+
 [[package]]
 name = "itoa"
 version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
 [[package]]
 name = "libc"
 version = "0.2.186"
@@ -43,9 +58,9 @@ checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
 
 [[package]]
 name = "memchr"
-version = "2.8.1"
+version = "2.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b947ae49db0d222b1dbc6b113ce7248a3fc3a6ca21b696717bfc000ba4484d8"
+checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
 
 [[package]]
 name = "memoffset"
@@ -151,18 +166,18 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.45"
+version = "1.0.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+checksum = "dfbc457d0c7a0759a614551b11a6409e5951f6c7537be1f1b7682b9ae9230368"
 dependencies = [
  "proc-macro2",
 ]
 
 [[package]]
 name = "rustversion"
-version = "1.0.22"
+version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f"
 
 [[package]]
 name = "serde"
@@ -209,7 +224,7 @@ dependencies = [
 
 [[package]]
 name = "speechmarkdown-python"
-version = "0.4.8"
+version = "0.4.10"
 dependencies = [
  "pyo3",
  "serde_json",
@@ -218,8 +233,9 @@ dependencies = [
 
 [[package]]
 name = "speechmarkdown-rust"
-version = "0.4.8"
+version = "0.4.10"
 dependencies = [
+ "ipa-translate",
  "quick-xml",
  "serde",
  "serde_json",
@@ -228,9 +244,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.117"
+version = "2.0.118"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -277,6 +293,6 @@ checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
 
 [[package]]
 name = "zmij"
-version = "1.0.21"
+version = "1.0.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
+checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/bindings/python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "speechmarkdown-python"
-version = "0.4.8"
+version = "0.4.10"
 edition = "2021"
 readme = "README.md"
 

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "speechmarkdown-rust"
-version = "0.4.8"
+version = "0.4.10"
 description = "SpeechMarkdown parser - convert SpeechMarkdown to SSML"
 readme = "README.md"
 

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/src/formatters/ssml/base.rs

@@ -600,6 +600,14 @@ impl SsmlFormatterBase {
                 }
                 attrs
             })),
+            "xsampa" | "praat" | "sil" | "branner" => {
+                let translated = translate_to_ipa(&key.to_lowercase(), value)?;
+                let mut attrs = vec![("alphabet".to_string(), "ipa".to_string())];
+                if !translated.is_empty() {
+                    attrs.push(("ph".to_string(), translated));
+                }
+                Some(("phoneme".to_string(), attrs))
+            }
             "sub" => {
                 if !value.is_empty() {
                     attributes.push(("alias".to_string(), value.to_string()));
@@ -735,6 +743,33 @@ impl SsmlFormatterBase {
     }
 }
 
+/// Translate a phonetic-alphabet value to IPA.
+///
+/// Recognized keys (lowercase): `xsampa`, `praat`, `sil`, `branner`. Returns
+/// `None` for any unrecognized key, or for every key when the
+/// `phonetic-translation` feature is disabled — callers treat `None` as
+/// "drop this modifier."
+///
+/// Conversion is infallible (garbage in, garbage out) per the upstream crate.
+#[cfg(feature = "phonetic-translation")]
+pub fn translate_to_ipa(key: &str, value: &str) -> Option<String> {
+    if value.is_empty() {
+        return Some(String::new());
+    }
+    match key {
+        "xsampa" => Some(ipa_translate::xsampa_to_ipa(value)),
+        "praat" => Some(ipa_translate::praat_to_ipa(value)),
+        "sil" => Some(ipa_translate::sil_to_ipa(value)),
+        "branner" => Some(ipa_translate::branner_to_ipa(value)),
+        _ => None,
+    }
+}
+
+#[cfg(not(feature = "phonetic-translation"))]
+pub fn translate_to_ipa(_key: &str, _value: &str) -> Option<String> {
+    None
+}
+
 pub fn format_attr_string_ordered(tag_name: &str, attributes: &TagAttrs) -> String {
     let fixed_order: Vec<&str> = match tag_name {
         "say-as" => vec!["interpret-as", "format"],
@@ -789,3 +824,64 @@ impl Formatter for SsmlFormatterBase {
         self.format_node_with_tags(node)
     }
 }
+
+#[cfg(test)]
+mod phonetic_alphabet_tests {
+    use super::*;
+    use crate::formatters::base::FormatterOptions;
+
+    fn fmt() -> SsmlFormatterBase {
+        SsmlFormatterBase::new(FormatterOptions::default())
+    }
+
+    #[cfg(feature = "phonetic-translation")]
+    #[test]
+    fn xsampa_value_becomes_ipa_phoneme_tag() {
+        let (tag, attrs) = fmt().attribute_to_tag("xsampa", "spitS").unwrap();
+        assert_eq!(tag, "phoneme");
+        assert_eq!(attrs_get(&attrs, "alphabet"), Some("ipa"));
+        assert_eq!(attrs_get(&attrs, "ph"), Some("spitʃ"));
+    }
+
+    #[cfg(feature = "phonetic-translation")]
+    #[test]
+    fn praat_sil_branner_all_emit_ipa_phoneme() {
+        let cases = [
+            ("praat", r"p\rta\:ft\^h", "pɹaːtʰ"),
+            ("sil", "si=l", "sɪl"),
+            ("branner", "br&ae):nE&r^", "bɹæːnɜ˞"),
+        ];
+        for (key, src, expected_ipa) in cases {
+            let (tag, attrs) = fmt().attribute_to_tag(key, src).unwrap();
+            assert_eq!(tag, "phoneme", "key {}", key);
+            assert_eq!(attrs_get(&attrs, "alphabet"), Some("ipa"), "key {}", key);
+            assert_eq!(
+                attrs_get(&attrs, "ph"),
+                Some(expected_ipa),
+                "key {}",
+                key
+            );
+        }
+    }
+
+    #[cfg(not(feature = "phonetic-translation"))]
+    #[test]
+    fn phonetic_keys_dropped_when_feature_disabled() {
+        for key in ["xsampa", "praat", "sil", "branner"] {
+            assert!(
+                fmt().attribute_to_tag(key, "anything").is_none(),
+                "{} should be dropped without phonetic-translation feature",
+                key
+            );
+        }
+    }
+
+    #[cfg(feature = "phonetic-translation")]
+    #[test]
+    fn empty_value_emits_phoneme_without_ph_attr() {
+        let (tag, attrs) = fmt().attribute_to_tag("xsampa", "").unwrap();
+        assert_eq!(tag, "phoneme");
+        assert_eq!(attrs_get(&attrs, "alphabet"), Some("ipa"));
+        assert_eq!(attrs_get(&attrs, "ph"), None);
+    }
+}

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/src/formatters/ssml/google_assistant.rs

@@ -26,7 +26,7 @@ impl GoogleAssistantSsmlFormatter {
             }
             "excited" | "disappointed" => None,
             "voice" | "lang" => None,
-            "ipa" => None,
+            "ipa" | "xsampa" | "praat" | "sil" | "branner" => None,
             "style" => {
                 if !value.is_empty() {
                     attributes.push(("name".to_string(), value.to_string()));
@@ -40,8 +40,8 @@ impl GoogleAssistantSsmlFormatter {
     fn format_google_text_modifier(&self, node: &AstNode) -> Result<String> {
         let mut tags: Vec<TagInfo> = Vec::new();
         let mut last_say_as: Option<TagInfo> = None;
-        let mut has_ipa = false;
-        let mut non_ipa_count = 0;
+        let mut phonetic_key: Option<String> = None;
+        let mut non_phonetic_count = 0;
 
         for key in &node.attribute_keys {
             let value = match node.attributes.get(key) {
@@ -49,10 +49,15 @@ impl GoogleAssistantSsmlFormatter {
                 None => continue,
             };
 
-            if key.to_lowercase() == "ipa" {
-                has_ipa = true;
+            if matches!(
+                key.to_lowercase().as_str(),
+                "ipa" | "xsampa" | "praat" | "sil" | "branner"
+            ) {
+                if phonetic_key.is_none() {
+                    phonetic_key = Some(key.clone());
+                }
             } else {
-                non_ipa_count += 1;
+                non_phonetic_count += 1;
             }
 
             if let Some(tag_info) = self.google_attribute_to_tag(key, value) {
@@ -71,15 +76,13 @@ impl GoogleAssistantSsmlFormatter {
             }
         }
 
-        if has_ipa && non_ipa_count == 0 {
+        if phonetic_key.is_some() && non_phonetic_count == 0 {
             return Ok(node.text.clone());
         }
 
-        if has_ipa {
-            if let Some(ipa_tag) = self
-                .base
-                .attribute_to_tag("ipa", node.attributes.get("ipa").unwrap_or(&String::new()))
-            {
+        if let Some(key) = phonetic_key {
+            let value = node.attributes.get(&key).cloned().unwrap_or_default();
+            if let Some(ipa_tag) = self.base.attribute_to_tag(&key, &value) {
                 tags.push(ipa_tag);
             }
         }

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/src/formatters/ssml/microsoft_azure.rs

@@ -416,11 +416,14 @@ impl Formatter for MicrosoftAzureSsmlFormatter {
             let use_mstts = trimmed.contains("mstts:express-as");
             if use_mstts {
                 Ok(format!(
-                    "<speak xmlns:mstts=\"https://www.w3.org/2001/mstts\">\n{}\n</speak>",
+                    "<speak version=\"1.0\" xmlns=\"http://www.w3.org/2001/10/synthesis\" xmlns:mstts=\"https://www.w3.org/2001/mstts\" xml:lang=\"en-US\">\n{}\n</speak>",
                     trimmed
                 ))
             } else {
-                Ok(format!("<speak>\n{}\n</speak>", trimmed))
+                Ok(format!(
+                    "<speak version=\"1.0\" xmlns=\"http://www.w3.org/2001/10/synthesis\" xml:lang=\"en-US\">\n{}\n</speak>",
+                    trimmed
+                ))
             }
         } else {
             Ok(content)

{speechmarkdown_rust-0.4.8 → speechmarkdown_rust-0.4.10}/tests/integration_test.rs

@@ -31,6 +31,21 @@ fn test_all_test_cases() {
             .and_then(|n| n.to_str())
             .unwrap_or("unknown");
 
+        // Fixtures that exercise the phonetic-translation feature; only
+        // run them when that feature is on.
+        #[cfg(not(feature = "phonetic-translation"))]
+        if matches!(
+            test_name,
+            "xsampa-standard"
+                | "xsampa-stress"
+                | "praat-standard"
+                | "sil-standard"
+                | "branner-standard"
+                | "combo-xsampa-emphasis"
+        ) {
+            continue;
+        }
+
         // Read the .smd input file
         let smd_file = test_dir.join(format!("{}.smd", test_name));
         if !smd_file.exists() {

speechmarkdown_rust-0.4.10/tests/test-data/test-data/branner-standard/branner-standard.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="bɹæːnɜ˞">branner</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/branner-standard/branner-standard.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="bɹæːnɜ˞">branner</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/branner-standard/branner-standard.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+say branner now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/branner-standard/branner-standard.smd

@@ -0,0 +1 @@
+say (branner)[branner:"br&ae):nE&r^"] now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/branner-standard/branner-standard.txt

@@ -0,0 +1 @@
+say branner now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/combo-xsampa-emphasis/combo-xsampa-emphasis.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+<emphasis level="strong"><phoneme alphabet="ipa" ph="spitʃ">hello</phoneme></emphasis>
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/combo-xsampa-emphasis/combo-xsampa-emphasis.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+<phoneme alphabet="ipa" ph="spitʃ">hello</phoneme>
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/combo-xsampa-emphasis/combo-xsampa-emphasis.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+<emphasis level="strong"><phoneme alphabet="ipa" ph="spitʃ">hello</phoneme></emphasis>
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/combo-xsampa-emphasis/combo-xsampa-emphasis.smd

@@ -0,0 +1 @@
+(hello)[xsampa:"spitS";emphasis:"strong"]

speechmarkdown_rust-0.4.10/tests/test-data/test-data/combo-xsampa-emphasis/combo-xsampa-emphasis.txt

@@ -0,0 +1 @@
+hello

speechmarkdown_rust-0.4.10/tests/test-data/test-data/praat-standard/praat-standard.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="pɹaːtʰ">praat</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/praat-standard/praat-standard.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="pɹaːtʰ">praat</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/praat-standard/praat-standard.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+say praat now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/praat-standard/praat-standard.smd

@@ -0,0 +1 @@
+say (praat)[praat:"p\rta\:ft\^h"] now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/praat-standard/praat-standard.txt

@@ -0,0 +1 @@
+say praat now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/sil-standard/sil-standard.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="sɪl">sil</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/sil-standard/sil-standard.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="sɪl">sil</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/sil-standard/sil-standard.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+say sil now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/sil-standard/sil-standard.smd

@@ -0,0 +1 @@
+say (sil)[sil:"si=l"] now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/sil-standard/sil-standard.txt

@@ -0,0 +1 @@
+say sil now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-standard/xsampa-standard.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="spitʃ">speech</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-standard/xsampa-standard.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="spitʃ">speech</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-standard/xsampa-standard.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+say speech now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-standard/xsampa-standard.smd

@@ -0,0 +1 @@
+say (speech)[xsampa:"spitS"] now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-standard/xsampa-standard.txt

@@ -0,0 +1 @@
+say speech now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-stress/xsampa-stress.alexa.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="həˈloʊ">hello</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-stress/xsampa-stress.azure.ssml

@@ -0,0 +1,3 @@
+<speak>
+say <phoneme alphabet="ipa" ph="həˈloʊ">hello</phoneme> now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-stress/xsampa-stress.google.ssml

@@ -0,0 +1,3 @@
+<speak>
+say hello now
+</speak>

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-stress/xsampa-stress.smd

@@ -0,0 +1 @@
+say (hello)[xsampa:"h@"loU"] now

speechmarkdown_rust-0.4.10/tests/test-data/test-data/xsampa-stress/xsampa-stress.txt

@@ -0,0 +1 @@
+say hello now