scriptconv 0.0.2a1__tar.gz → 0.0.3a1__tar.gz

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.2a1
-Summary: Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo
+Version: 0.0.3a1
+Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv
 Project-URL: Issues, https://github.com/TigreGotico/scriptconv/issues
-Keywords: ipa,arpabet,x-sampa,lexique,buckwalter,hangul,script,iso15924,tts,g2p,phoneme
+Keywords: ipa,arpabet,x-sampa,kirshenbaum,cotovia,rfe,lexique,buckwalter,hangul,jamo,kana,transliteration,notation,phoneme,phonetic-alphabet,script,iso15924,unicode,tts,g2p
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -31,12 +31,21 @@ Dynamic: license-file
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.
@@ -75,7 +84,8 @@ from scriptconv import (
     xsampa_to_ipa, ipa_to_xsampa,
     buckwalter_to_arabic, arabic_to_buckwalter,
     lexique_to_ipa, ipa_to_lexique,
-    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia, looks_like_ipa,
+    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia,
+    rfe_to_ipa, ipa_to_rfe, looks_like_ipa,
     decompose_hangul, hira_to_kana, kana_to_hira,
     convert, can_convert, convert_batch, Notation, NOTATION_INFO,
 )
@@ -110,6 +120,9 @@ ipa_to_kirshenbaum("ŋ")             # "N"
 cotovia_to_ipa("karro")             # "karo"  (Galician Cotovía TTS notation)
 ipa_to_cotovia("ʎ")                 # "L"
 
+rfe_to_ipa("kaša")                  # "kaʃa"  (Spanish/Romance RFE alphabet)
+ipa_to_rfe("ɲ")                     # "ñ"
+
 looks_like_ipa("pʰɑtʃ")             # True  (heuristic: has IPA-distinctive symbols)
 looks_like_ipa("hello")             # False
 
@@ -142,7 +155,7 @@ python -m scriptconv lang ko
 | Module | Contents |
 |--------|----------|
 | `scriptconv.scripts` | `Script` dataclass (with `script_type`), `SCRIPT_REGISTRY` (34 scripts), `detect_script`, `char_script`, `script_distribution`, `script_runs`, `base_direction`, `lang_to_script`, `script_to_langs`, `normalize_script_tag` |
-| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA), `looks_like_ipa` detector |
+| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA, RFE ↔ IPA), `looks_like_ipa` detector |
 | `scriptconv.translit` | `decompose_hangul` (Hangul blocks → jamo, compatibility or conjoining), `hira_to_kana`/`kana_to_hira` — all orthographic only |
 
 ## Documentation
@@ -172,6 +185,7 @@ Runnable scripts in [examples/](examples/):
 | `13_script_runs.py` | Per-script segmentation of mixed-script text |
 | `14_kana_transliteration.py` | Hiragana ↔ Katakana |
 | `15_cotovia.py` | Cotovía (Galician TTS notation) ↔ IPA |
+| `16_rfe.py` | RFE (Spanish/Romance philology alphabet) ↔ IPA |
 
 ## Fidelity guarantees
 
@@ -187,6 +201,7 @@ round-trip is exact and what happens to a symbol the table does not know.
 | **Lexique ↔ IPA** | Exact except the `°`/`3` schwa pair (both → `ə`; reverse always → `°`) | Exact | Passed through unchanged |
 | **Kirshenbaum ↔ IPA** | Exact | **Lossy** — restricted ASCII inventory; IPA outside it passes through | Passed through unchanged |
 | **Cotovía ↔ IPA** | Exact except the three `L`/`Z`/`jj` symbols for `ʎ` normalise to `L` | **Lossy** — Galician/Spanish inventory; IPA outside it passes through | Passed through unchanged |
+| **RFE ↔ IPA** | Exact except `ñ`/`n̮` for `ɲ` normalise to `ñ` | **Lossy** — core Spanish/Romance inventory; IPA outside it passes through | Passed through unchanged |
 
 This table is also available programmatically via `NOTATION_INFO`
 (`NotationInfo` records with `lossless_to_ipa`, `lossless_from_ipa`,
@@ -213,4 +228,5 @@ Derived tables used internally:
 | Lexique phoneme codes | New, B. & Pallier, C. — *Manuel de Lexique 3* v3.11, Tableau 2; [chrplr/openlexicon](https://github.com/chrplr/openlexicon) | CC BY-SA 4.0 |
 | Kirshenbaum ↔ IPA | Kirshenbaum 1993 ASCII-IPA standard (comp.speech), cross-checked against espeak-ng | — (factual symbol mapping) |
 | Cotovía ↔ IPA | Universidade de Vigo GTM Cotovía TTS project (`fonemas.cpp`) | — (factual symbol mapping) |
+| RFE ↔ IPA | RFE phonetic alphabet (Revista de Filología Española, 1915) | — (factual symbol mapping) |
 | Hangul jamo tables | [stannam/hangul_to_ipa](https://github.com/stannam/hangul_to_ipa) | — |

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/README.md

@@ -4,12 +4,21 @@
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.
@@ -48,7 +57,8 @@ from scriptconv import (
     xsampa_to_ipa, ipa_to_xsampa,
     buckwalter_to_arabic, arabic_to_buckwalter,
     lexique_to_ipa, ipa_to_lexique,
-    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia, looks_like_ipa,
+    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia,
+    rfe_to_ipa, ipa_to_rfe, looks_like_ipa,
     decompose_hangul, hira_to_kana, kana_to_hira,
     convert, can_convert, convert_batch, Notation, NOTATION_INFO,
 )
@@ -83,6 +93,9 @@ ipa_to_kirshenbaum("ŋ")             # "N"
 cotovia_to_ipa("karro")             # "karo"  (Galician Cotovía TTS notation)
 ipa_to_cotovia("ʎ")                 # "L"
 
+rfe_to_ipa("kaša")                  # "kaʃa"  (Spanish/Romance RFE alphabet)
+ipa_to_rfe("ɲ")                     # "ñ"
+
 looks_like_ipa("pʰɑtʃ")             # True  (heuristic: has IPA-distinctive symbols)
 looks_like_ipa("hello")             # False
 
@@ -115,7 +128,7 @@ python -m scriptconv lang ko
 | Module | Contents |
 |--------|----------|
 | `scriptconv.scripts` | `Script` dataclass (with `script_type`), `SCRIPT_REGISTRY` (34 scripts), `detect_script`, `char_script`, `script_distribution`, `script_runs`, `base_direction`, `lang_to_script`, `script_to_langs`, `normalize_script_tag` |
-| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA), `looks_like_ipa` detector |
+| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA, RFE ↔ IPA), `looks_like_ipa` detector |
 | `scriptconv.translit` | `decompose_hangul` (Hangul blocks → jamo, compatibility or conjoining), `hira_to_kana`/`kana_to_hira` — all orthographic only |
 
 ## Documentation
@@ -145,6 +158,7 @@ Runnable scripts in [examples/](examples/):
 | `13_script_runs.py` | Per-script segmentation of mixed-script text |
 | `14_kana_transliteration.py` | Hiragana ↔ Katakana |
 | `15_cotovia.py` | Cotovía (Galician TTS notation) ↔ IPA |
+| `16_rfe.py` | RFE (Spanish/Romance philology alphabet) ↔ IPA |
 
 ## Fidelity guarantees
 
@@ -160,6 +174,7 @@ round-trip is exact and what happens to a symbol the table does not know.
 | **Lexique ↔ IPA** | Exact except the `°`/`3` schwa pair (both → `ə`; reverse always → `°`) | Exact | Passed through unchanged |
 | **Kirshenbaum ↔ IPA** | Exact | **Lossy** — restricted ASCII inventory; IPA outside it passes through | Passed through unchanged |
 | **Cotovía ↔ IPA** | Exact except the three `L`/`Z`/`jj` symbols for `ʎ` normalise to `L` | **Lossy** — Galician/Spanish inventory; IPA outside it passes through | Passed through unchanged |
+| **RFE ↔ IPA** | Exact except `ñ`/`n̮` for `ɲ` normalise to `ñ` | **Lossy** — core Spanish/Romance inventory; IPA outside it passes through | Passed through unchanged |
 
 This table is also available programmatically via `NOTATION_INFO`
 (`NotationInfo` records with `lossless_to_ipa`, `lossless_from_ipa`,
@@ -186,4 +201,5 @@ Derived tables used internally:
 | Lexique phoneme codes | New, B. & Pallier, C. — *Manuel de Lexique 3* v3.11, Tableau 2; [chrplr/openlexicon](https://github.com/chrplr/openlexicon) | CC BY-SA 4.0 |
 | Kirshenbaum ↔ IPA | Kirshenbaum 1993 ASCII-IPA standard (comp.speech), cross-checked against espeak-ng | — (factual symbol mapping) |
 | Cotovía ↔ IPA | Universidade de Vigo GTM Cotovía TTS project (`fonemas.cpp`) | — (factual symbol mapping) |
+| RFE ↔ IPA | RFE phonetic alphabet (Revista de Filología Española, 1915) | — (factual symbol mapping) |
 | Hangul jamo tables | [stannam/hangul_to_ipa](https://github.com/stannam/hangul_to_ipa) | — |

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "scriptconv"
 dynamic = ["version", "dependencies"]
-description = "Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo"
+description = "Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana"
 readme = "README.md"
 license = {text = "Apache-2.0"}
 requires-python = ">=3.10"
@@ -22,7 +22,11 @@ classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
 ]
-keywords = ["ipa", "arpabet", "x-sampa", "lexique", "buckwalter", "hangul", "script", "iso15924", "tts", "g2p", "phoneme"]
+keywords = [
+    "ipa", "arpabet", "x-sampa", "kirshenbaum", "cotovia", "rfe", "lexique",
+    "buckwalter", "hangul", "jamo", "kana", "transliteration", "notation",
+    "phoneme", "phonetic-alphabet", "script", "iso15924", "unicode", "tts", "g2p",
+]
 
 [tool.setuptools.dynamic]
 version = {attr = "scriptconv.version.VERSION_STR"}

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/scriptconv/__init__.py

@@ -52,6 +52,8 @@ from scriptconv.notation import (
     ipa_to_kirshenbaum,
     cotovia_to_ipa,
     ipa_to_cotovia,
+    rfe_to_ipa,
+    ipa_to_rfe,
     looks_like_ipa,
 )
 from scriptconv.translit import (
@@ -91,6 +93,8 @@ __all__ = [
     "ipa_to_kirshenbaum",
     "cotovia_to_ipa",
     "ipa_to_cotovia",
+    "rfe_to_ipa",
+    "ipa_to_rfe",
     "looks_like_ipa",
     # translit
     "decompose_hangul",

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/scriptconv/notation.py

@@ -39,6 +39,8 @@ __all__ = [
     "ipa_to_kirshenbaum",
     "cotovia_to_ipa",
     "ipa_to_cotovia",
+    "rfe_to_ipa",
+    "ipa_to_rfe",
     "looks_like_ipa",
 ]
 
@@ -54,6 +56,7 @@ class Notation(str, Enum):
     LEXIQUE = "lexique"  # Lexique one-char-per-phoneme French notation
     KIRSHENBAUM = "kirshenbaum"  # ASCII-IPA (espeak-ng native notation)
     COTOVIA = "cotovia"  # Universidade de Vigo Cotovía TTS notation (gl)
+    RFE = "rfe"  # Revista de Filología Española phonetic alphabet
 
     def __repr__(self) -> str:
         return f"Notation.{self.name}"
@@ -786,6 +789,126 @@ def ipa_to_cotovia(ipa: str) -> str:
     return "".join(result)
 
 
+# ---------------------------------------------------------------------------
+# RFE (Revista de Filología Española) ↔ IPA
+#
+# The RFE phonetic alphabet (Navarro Tomás, Revista de Filología Española,
+# 1915) is the traditional transcription system of Spanish and Romance
+# philology. This is its core, well-attested inventory; rare interdental and
+# variant diacritic symbols from the full standard are omitted. Symbols are
+# matched longest-first (combining-mark symbols before their base letters).
+# Reference: RFE Phonetic Alphabet
+# (https://en.wikipedia.org/wiki/RFE_Phonetic_Alphabet).
+# ---------------------------------------------------------------------------
+
+_RFE_TO_IPA: dict[str, str] = {
+    # Combining-mark symbols (longest-match first)
+    "r̄": "r",    # r + macron = alveolar trill (plain r = tap ɾ)
+    "n̮": "ɲ",   # n + breve below = palatal nasal ɲ
+    "l̮": "ʎ",   # l + breve below = palatal lateral ʎ
+    # Palatal / postalveolar
+    "ĉ": "tʃ",   # ĉ = tʃ
+    "š": "ʃ",    # š = ʃ
+    "ž": "ʒ",    # ž = ʒ
+    "ŷ": "ɟʝ",  # ŷ = ɟʝ (voiced palatal affricate)
+    "ñ": "ɲ",    # ñ = ɲ
+    "y": "ʝ",         # y = ʝ
+    "j": "j",              # j = j
+    # Spanish approximant/fricative allophones
+    "ƀ": "β",    # ƀ = β
+    "đ": "ð",    # đ = ð
+    "ǥ": "ɣ",    # ǥ = ɣ
+    # Other consonants
+    "θ": "θ",    # θ = θ
+    "x": "x",
+    "ł": "ɫ",    # ł = ɫ (velarized l)
+    "ŋ": "ŋ",    # ŋ = ŋ
+    "w": "w",
+    "h": "h",
+    "b": "b",
+    "p": "p",
+    "t": "t",
+    "d": "d",
+    "k": "k",
+    "g": "ɡ",         # g = ɡ (script g, matching the other tables)
+    "f": "f",
+    "v": "v",
+    "s": "s",
+    "z": "z",
+    "m": "m",
+    "n": "n",
+    "l": "l",
+    "r": "ɾ",         # r = tap ɾ
+    # Vowels
+    "a": "a", "e": "e", "i": "i", "o": "o", "u": "u",
+    "ə": "ə",    # ə = ə
+}
+
+# Reverse: IPA → RFE. First-wins deduplicates; pin the canonical RFE spellings
+# for the palatal nasal (ñ) and the trill/tap pair.
+_IPA_TO_RFE: dict[str, str] = {}
+for _rfe, _ip in _RFE_TO_IPA.items():
+    _IPA_TO_RFE.setdefault(_ip, _rfe)
+_IPA_TO_RFE["ɲ"] = "ñ"   # ɲ → ñ (canonical, not the n̮ variant)
+
+_RFE_KEYS_SORTED = sorted(_RFE_TO_IPA.keys(), key=len, reverse=True)
+_RFE_RE = re.compile("|".join(re.escape(x) for x in _RFE_KEYS_SORTED))
+_IPA_RFE_KEYS_SORTED = sorted(_IPA_TO_RFE.keys(), key=len, reverse=True)
+_IPA_RFE_RE = re.compile("|".join(re.escape(x) for x in _IPA_RFE_KEYS_SORTED))
+
+
+def rfe_to_ipa(rfe: str) -> str:
+    """Convert an RFE (Revista de Filología Española) string to IPA.
+
+    Multi-character symbols are matched longest-first. Characters outside the
+    table pass through unchanged.
+
+    Examples
+    --------
+    >>> rfe_to_ipa("š")
+    'ʃ'
+    >>> rfe_to_ipa("kaša")
+    'kaʃa'
+    """
+    result = []
+    pos = 0
+    while pos < len(rfe):
+        m = _RFE_RE.match(rfe, pos)
+        if m:
+            result.append(_RFE_TO_IPA[m.group(0)])
+            pos = m.end()
+        else:
+            result.append(rfe[pos])
+            pos += 1
+    return "".join(result)
+
+
+def ipa_to_rfe(ipa: str) -> str:
+    """Convert an IPA string to RFE (Revista de Filología Española) notation.
+
+    Multi-character IPA symbols are matched longest-first. Characters outside
+    the table pass through unchanged.
+
+    Examples
+    --------
+    >>> ipa_to_rfe("ʃ")
+    'š'
+    >>> ipa_to_rfe("ɲ")
+    'ñ'
+    """
+    result = []
+    pos = 0
+    while pos < len(ipa):
+        m = _IPA_RFE_RE.match(ipa, pos)
+        if m:
+            result.append(_IPA_TO_RFE[m.group(0)])
+            pos = m.end()
+        else:
+            result.append(ipa[pos])
+            pos += 1
+    return "".join(result)
+
+
 # ---------------------------------------------------------------------------
 # convert — facade routing through IPA where no direct map exists
 # ---------------------------------------------------------------------------
@@ -857,6 +980,7 @@ _TO_IPA: dict[Notation, "callable"] = {
     Notation.LEXIQUE: lexique_to_ipa,
     Notation.KIRSHENBAUM: kirshenbaum_to_ipa,
     Notation.COTOVIA: cotovia_to_ipa,
+    Notation.RFE: rfe_to_ipa,
 }
 _FROM_IPA: dict[Notation, "callable"] = {
     Notation.ARPA: ipa_to_arpa,
@@ -864,6 +988,7 @@ _FROM_IPA: dict[Notation, "callable"] = {
     Notation.LEXIQUE: ipa_to_lexique,
     Notation.KIRSHENBAUM: ipa_to_kirshenbaum,
     Notation.COTOVIA: ipa_to_cotovia,
+    Notation.RFE: ipa_to_rfe,
 }
 _DIRECT_PAIRS: dict[tuple[Notation, Notation], "callable"] = {
     (Notation.BUCKWALTER, Notation.ARABIC): buckwalter_to_arabic,
@@ -974,6 +1099,11 @@ NOTATION_INFO: dict[Notation, NotationInfo] = {
         token_separated=False,
         reference="Universidade de Vigo GTM Cotovía TTS (fonemas.cpp)",
     ),
+    Notation.RFE: NotationInfo(
+        Notation.RFE, lossless_to_ipa=False, lossless_from_ipa=False,
+        token_separated=False,
+        reference="RFE phonetic alphabet (Revista de Filología Española, 1915)",
+    ),
     Notation.BUCKWALTER: NotationInfo(
         Notation.BUCKWALTER, lossless_to_ipa=True, lossless_from_ipa=False,
         token_separated=False,

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/scriptconv/version.py

@@ -1,7 +1,7 @@
 # START_VERSION_BLOCK
 VERSION_MAJOR = 0
 VERSION_MINOR = 0
-VERSION_BUILD = 2
+VERSION_BUILD = 3
 VERSION_ALPHA = 1
 # END_VERSION_BLOCK
 

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/scriptconv.egg-info/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.2a1
-Summary: Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo
+Version: 0.0.3a1
+Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv
 Project-URL: Issues, https://github.com/TigreGotico/scriptconv/issues
-Keywords: ipa,arpabet,x-sampa,lexique,buckwalter,hangul,script,iso15924,tts,g2p,phoneme
+Keywords: ipa,arpabet,x-sampa,kirshenbaum,cotovia,rfe,lexique,buckwalter,hangul,jamo,kana,transliteration,notation,phoneme,phonetic-alphabet,script,iso15924,unicode,tts,g2p
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -31,12 +31,21 @@ Dynamic: license-file
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.
@@ -75,7 +84,8 @@ from scriptconv import (
     xsampa_to_ipa, ipa_to_xsampa,
     buckwalter_to_arabic, arabic_to_buckwalter,
     lexique_to_ipa, ipa_to_lexique,
-    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia, looks_like_ipa,
+    kirshenbaum_to_ipa, ipa_to_kirshenbaum, cotovia_to_ipa, ipa_to_cotovia,
+    rfe_to_ipa, ipa_to_rfe, looks_like_ipa,
     decompose_hangul, hira_to_kana, kana_to_hira,
     convert, can_convert, convert_batch, Notation, NOTATION_INFO,
 )
@@ -110,6 +120,9 @@ ipa_to_kirshenbaum("ŋ")             # "N"
 cotovia_to_ipa("karro")             # "karo"  (Galician Cotovía TTS notation)
 ipa_to_cotovia("ʎ")                 # "L"
 
+rfe_to_ipa("kaša")                  # "kaʃa"  (Spanish/Romance RFE alphabet)
+ipa_to_rfe("ɲ")                     # "ñ"
+
 looks_like_ipa("pʰɑtʃ")             # True  (heuristic: has IPA-distinctive symbols)
 looks_like_ipa("hello")             # False
 
@@ -142,7 +155,7 @@ python -m scriptconv lang ko
 | Module | Contents |
 |--------|----------|
 | `scriptconv.scripts` | `Script` dataclass (with `script_type`), `SCRIPT_REGISTRY` (34 scripts), `detect_script`, `char_script`, `script_distribution`, `script_runs`, `base_direction`, `lang_to_script`, `script_to_langs`, `normalize_script_tag` |
-| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA), `looks_like_ipa` detector |
+| `scriptconv.notation` | `Notation` enum, `NotationInfo`/`NOTATION_INFO` fidelity registry, `convert` facade, `can_convert` predicate, `convert_batch` generator, pair-wise converters (ARPABET ↔ IPA, X-SAMPA ↔ IPA, Buckwalter ↔ Arabic, Lexique ↔ IPA, Kirshenbaum ↔ IPA, Cotovía ↔ IPA, RFE ↔ IPA), `looks_like_ipa` detector |
 | `scriptconv.translit` | `decompose_hangul` (Hangul blocks → jamo, compatibility or conjoining), `hira_to_kana`/`kana_to_hira` — all orthographic only |
 
 ## Documentation
@@ -172,6 +185,7 @@ Runnable scripts in [examples/](examples/):
 | `13_script_runs.py` | Per-script segmentation of mixed-script text |
 | `14_kana_transliteration.py` | Hiragana ↔ Katakana |
 | `15_cotovia.py` | Cotovía (Galician TTS notation) ↔ IPA |
+| `16_rfe.py` | RFE (Spanish/Romance philology alphabet) ↔ IPA |
 
 ## Fidelity guarantees
 
@@ -187,6 +201,7 @@ round-trip is exact and what happens to a symbol the table does not know.
 | **Lexique ↔ IPA** | Exact except the `°`/`3` schwa pair (both → `ə`; reverse always → `°`) | Exact | Passed through unchanged |
 | **Kirshenbaum ↔ IPA** | Exact | **Lossy** — restricted ASCII inventory; IPA outside it passes through | Passed through unchanged |
 | **Cotovía ↔ IPA** | Exact except the three `L`/`Z`/`jj` symbols for `ʎ` normalise to `L` | **Lossy** — Galician/Spanish inventory; IPA outside it passes through | Passed through unchanged |
+| **RFE ↔ IPA** | Exact except `ñ`/`n̮` for `ɲ` normalise to `ñ` | **Lossy** — core Spanish/Romance inventory; IPA outside it passes through | Passed through unchanged |
 
 This table is also available programmatically via `NOTATION_INFO`
 (`NotationInfo` records with `lossless_to_ipa`, `lossless_from_ipa`,
@@ -213,4 +228,5 @@ Derived tables used internally:
 | Lexique phoneme codes | New, B. & Pallier, C. — *Manuel de Lexique 3* v3.11, Tableau 2; [chrplr/openlexicon](https://github.com/chrplr/openlexicon) | CC BY-SA 4.0 |
 | Kirshenbaum ↔ IPA | Kirshenbaum 1993 ASCII-IPA standard (comp.speech), cross-checked against espeak-ng | — (factual symbol mapping) |
 | Cotovía ↔ IPA | Universidade de Vigo GTM Cotovía TTS project (`fonemas.cpp`) | — (factual symbol mapping) |
+| RFE ↔ IPA | RFE phonetic alphabet (Revista de Filología Española, 1915) | — (factual symbol mapping) |
 | Hangul jamo tables | [stannam/hangul_to_ipa](https://github.com/stannam/hangul_to_ipa) | — |

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/tests/test_examples.py

@@ -111,3 +111,9 @@ def test_15_cotovia():
     r = _run(EXAMPLES_DIR / "15_cotovia.py")
     assert r.returncode == 0, r.stderr
     assert r.stdout.strip()
+
+
+def test_16_rfe():
+    r = _run(EXAMPLES_DIR / "16_rfe.py")
+    assert r.returncode == 0, r.stderr
+    assert r.stdout.strip()

{scriptconv-0.0.2a1 → scriptconv-0.0.3a1}/tests/test_notation.py

@@ -947,7 +947,7 @@ def test_notation_enum_values():
 
 
 def test_notation_enum_count():
-    assert len(Notation) == 8
+    assert len(Notation) == 9
 
 
 def test_notation_str():
@@ -1108,3 +1108,43 @@ def test_cotovia_pause_marker_not_a_phoneme():
     assert cotovia_to_ipa("#") == "#"
     # p/a/u are ordinary phonemes, converted independently.
     assert cotovia_to_ipa("pau") == "pau"
+
+
+# ---------------------------------------------------------------------------
+# RFE (Revista de Filología Española) ↔ IPA
+# ---------------------------------------------------------------------------
+
+from scriptconv.notation import rfe_to_ipa, ipa_to_rfe  # noqa: E402
+
+
+@pytest.mark.parametrize("rfe, ipa", [
+    ("š", "ʃ"), ("ž", "ʒ"), ("ĉ", "tʃ"), ("y", "ʝ"), ("ŷ", "ɟʝ"),
+    ("ñ", "ɲ"), ("n̮", "ɲ"), ("l̮", "ʎ"),
+    ("ƀ", "β"), ("đ", "ð"), ("ǥ", "ɣ"), ("θ", "θ"), ("ł", "ɫ"),
+    ("r", "ɾ"), ("r̄", "r"),
+    ("g", "ɡ"),
+    ("kaša", "kaʃa"),
+])
+def test_rfe_to_ipa(rfe, ipa):
+    assert rfe_to_ipa(rfe) == ipa
+
+
+@pytest.mark.parametrize("ipa, rfe", [
+    ("ʃ", "š"), ("ʒ", "ž"), ("tʃ", "ĉ"), ("ʝ", "y"),
+    ("ɲ", "ñ"),      # canonical, not the n̮ variant
+    ("ʎ", "l̮"),
+    ("β", "ƀ"), ("ð", "đ"), ("ɣ", "ǥ"),
+    ("ɾ", "r"), ("r", "r̄"),
+])
+def test_ipa_to_rfe(ipa, rfe):
+    assert ipa_to_rfe(ipa) == rfe
+
+
+def test_rfe_tap_trill_round_trip():
+    assert ipa_to_rfe(rfe_to_ipa("far̄a")) == "far̄a"   # trill
+    assert ipa_to_rfe(rfe_to_ipa("kara")) == "kara"     # tap
+
+
+def test_convert_routes_through_rfe():
+    assert convert("š", "rfe", "x-sampa") == "S"
+    assert convert("ʃ", "ipa", "rfe") == "š"