hyperglot 0.8.1__tar.gz → 0.8.2__tar.gz

{hyperglot-0.8.1 → hyperglot-0.8.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hyperglot
-Version: 0.8.1
+Version: 0.8.2
 Summary: Detect language support for font binaries
 Author-email: Johannes Neumeier - Rosetta <johannes@rosettatype.com>
 License-Expression: Apache-2.0
@@ -17,7 +17,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: packaging>=26.0
 Requires-Dist: click>=7.0
-Requires-Dist: fonttools>=4.50.0
+Requires-Dist: fonttools[woff]>=4.50.0
 Requires-Dist: uharfbuzz>=0.39.0
 Requires-Dist: pyyaml>=6.0.0
 Requires-Dist: colorlog>=6.4.1
@@ -42,7 +42,14 @@ Hyperglot is available as:
 📖 [Learn more about Hyperglot](https://hyperglot.rosettatype.com/about)  
 🙋 [Read the FAQ](FAQ.md)
 
-💰 [Sponsor via GitHub](https://github.com/sponsors/rosettatype) or directly via [Hyperglot sponsorship](https://hyperglot.rosettatype.com/sponsor). Any and all contributions are much appreciated! 🙏
+## 💰 Sponsor
+
+We welcome contributions to support our editorial work via Rosetta’s [GitHub](https://github.com/sponsors/rosettatype) or [Stripe](https://donate.stripe.com/3cI00j3PD0w53fwdx8dfG0f). Any level of support is greatly appreciated and helps sustain the project. 🙏
+
+- Contributions above €/$1,000 will be acknowledged below and on the website (About page) for a minimum of five years.
+- Contributions above €/$3,000 will also be featured in the website header as “Funded by…” for one year.
+
+For more details, feel free to get in touch via email.
 
 ## Data validity & contributing
 
@@ -105,6 +112,8 @@ Besides the main `hyperglot` command used for font inspection, the package also
 
 ### Basic usage
 
+Font inspection supports TTF, OTF, WOFF and WOFF2 files.
+
 Use:
 
 ```shell

{hyperglot-0.8.1 → hyperglot-0.8.2}/README.md

@@ -11,7 +11,14 @@ Hyperglot is available as:
 📖 [Learn more about Hyperglot](https://hyperglot.rosettatype.com/about)  
 🙋 [Read the FAQ](FAQ.md)
 
-💰 [Sponsor via GitHub](https://github.com/sponsors/rosettatype) or directly via [Hyperglot sponsorship](https://hyperglot.rosettatype.com/sponsor). Any and all contributions are much appreciated! 🙏
+## 💰 Sponsor
+
+We welcome contributions to support our editorial work via Rosetta’s [GitHub](https://github.com/sponsors/rosettatype) or [Stripe](https://donate.stripe.com/3cI00j3PD0w53fwdx8dfG0f). Any level of support is greatly appreciated and helps sustain the project. 🙏
+
+- Contributions above €/$1,000 will be acknowledged below and on the website (About page) for a minimum of five years.
+- Contributions above €/$3,000 will also be featured in the website header as “Funded by…” for one year.
+
+For more details, feel free to get in touch via email.
 
 ## Data validity & contributing
 
@@ -74,6 +81,8 @@ Besides the main `hyperglot` command used for font inspection, the package also
 
 ### Basic usage
 
+Font inspection supports TTF, OTF, WOFF and WOFF2 files.
+
 Use:
 
 ```shell

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/__init__.py

@@ -8,7 +8,7 @@ from enum import Enum
 
 from hyperglot.utils import AllChoicesEnumMixin, ConvenientEnumMixin
 
-__version__ = "0.8.1"
+__version__ = "0.8.2"
 
 DB = path.abspath(path.join(path.dirname(__file__), "data"))
 DB_EXTRA = path.abspath(path.join(path.dirname(__file__), "extra_data"))
@@ -16,8 +16,8 @@ DB_CHECKS = path.abspath(path.join(path.dirname(__file__), "checks"))
 
 LANGUAGE_CACHE_FILE = ".hyperglot-cache"
 
-# ~~DONE Refactor these levels and status as Enum's~~
-# TODO Eventaully remove deprecated "CONSTANTS"
+# Only show a cache rebuild warning once per session, not once per language!
+LANGUAGE_CACHE_MISMATCH_WARNING_SHOWN = False
 
 
 class SupportLevel(AllChoicesEnumMixin, Enum):

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/checkbase.py

@@ -14,44 +14,20 @@ if TYPE_CHECKING:
 class CheckBase:
 
     # Unicode constants used in some of the checks
-    VIRAMA = chr(0x094D)
+    # Futher script-specific constant can be added in subclasses
     ZWJ = chr(0x200D)
     ZWNJ = chr(0x200C)
     DOTTED_CIRCLE = chr(0x25CC)
-    BRAHMIC_CATEGORIES = {
-        "+": [chr(0x094D)],
-        "V": [
-            chr(c)
-            for c in list(range(0x0904, 0x0914 + 1))
-            + [0x0960, 0x0961]
-            + list(range(0x0973, 0x0977 + 1))
-        ],
-        "C": [
-            chr(c)
-            for c in list(range(0x0915, 0x0939 + 1))
-            + list(range(0x0958, 0x095F + 1))
-            + list(range(0x0978, 0x097F + 1))
-        ],
-        "D": [
-            chr(c)
-            for c in [0x093A, 0x093B]
-            + list(range(0x093E, 0x094C + 1))
-            + [0x094E, 0x094F]
-            + [0x0955, 0x0956, 0x0957]
-            + [0x0962, 0x0963]
-        ],
-        "M": [chr(0x093C)],
-        "m": [chr(c) for c in list(range(0x0900, 0x0903 + 1))],
-        "P": [chr(c) for c in [0x093D, 0x0964, 0x0965]],
-        "Z": [chr(0x200C)],
-        "z": [chr(0x200D)],
-    }
 
     # Conditions by which to determined if a check should run for a given
-    # orthography
+    # orthography.
+    # Multiple condition attributes are INTERSECTed, e.g. if both "scripts" and
+    # "attributes" are provided, the check will run if an orthography matches
+    # any of the scripts AND has any of the attributes.
     conditions = {
-        # e.g.
-        # "script": "Devanagari",
+        # Match any of the given scripts
+        # "scripts": ("Devanagari",),
+        # Match any of the given orthography attributes, e.g. "base", "auxiliary", "mark", "combinations"
         # "attributes": ("combinations",),
     }
 
@@ -173,10 +149,41 @@ class BrahmiBaseCheck(CheckBase):
     A more specific base check for Brahmi scripts.
     """
 
+    VIRAMA = chr(0x094D)
+    BRAHMIC_CATEGORIES = {
+        "+": [chr(0x094D)],
+        "V": [
+            chr(c)
+            for c in list(range(0x0904, 0x0914 + 1))
+            + [0x0960, 0x0961]
+            + list(range(0x0973, 0x0977 + 1))
+        ],
+        "C": [
+            chr(c)
+            for c in list(range(0x0915, 0x0939 + 1))
+            + list(range(0x0958, 0x095F + 1))
+            + list(range(0x0978, 0x097F + 1))
+        ],
+        "D": [
+            chr(c)
+            for c in [0x093A, 0x093B]
+            + list(range(0x093E, 0x094C + 1))
+            + [0x094E, 0x094F]
+            + [0x0955, 0x0956, 0x0957]
+            + [0x0962, 0x0963]
+        ],
+        "M": [chr(0x093C)],
+        "m": [chr(c) for c in list(range(0x0900, 0x0903 + 1))],
+        "P": [chr(c) for c in [0x093D, 0x0964, 0x0965]],
+        "Z": [chr(0x200C)],
+        "z": [chr(0x200D)],
+    }
+
     conditions = {
-        "script": "Devanagari",
+        "scripts": ("Devanagari",),
         "attributes": ("combinations",),
     }
+
     requires_font = True
 
     def precheck(

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/checker.py

@@ -3,6 +3,7 @@ from fontTools.ttLib import TTFont
 import os
 import sys
 import importlib.util
+import functools
 from typing import List, Set
 from collections.abc import Iterable
 
@@ -36,6 +37,43 @@ def format_missing_unicodes(codepoints: Set[str], reference) -> str:
         return (" ".join(["%s (%s)" % (c, str(ord(c))) for c in diff]),)
 
 
+@functools.cache
+def _load_check_modules() -> tuple:
+    """
+    Import every check module in lib/hyperglot/checks, once per process.
+
+    Checks are matched against each orthography of each language, and importing
+    the modules anew every time made loading them the bulk of a check's run
+    time. The modules only hold classes; each run still gets fresh Check
+    instances, so no per-run state is shared.
+    """
+    modules = []
+    check_files = [
+        f for f in os.listdir(os.path.join(DB_CHECKS)) if f.endswith(".py")
+    ]
+
+    for f in check_files:
+        module_file = os.path.join(DB_CHECKS, f)
+        module_name = os.path.splitext(f)[0]
+
+        try:
+            spec = importlib.util.spec_from_file_location(module_name, module_file)
+            c = importlib.util.module_from_spec(spec)
+            sys.modules[module_name] = c
+            spec.loader.exec_module(c)
+            check = c.Check()
+        except Exception as e:
+            log.error(f"Failed to instantiate check {module_name}. Fix the below:")
+            raise e
+
+        if not isinstance(check, CheckBase):
+            raise Exception(f"Check {module_name} needs to subclass CheckBase!")
+
+        modules.append((module_name, c))
+
+    return tuple(modules)
+
+
 class Checker:
     """
     A base class for CharsetChecker and FontChecker encapsulating language
@@ -58,26 +96,8 @@ class Checker:
         """
         checks = []
 
-        check_files = [
-            f for f in os.listdir(os.path.join(DB_CHECKS)) if f.endswith(".py")
-        ]
-
-        for f in check_files:
-            module_file = os.path.join(DB_CHECKS, f)
-            module_name = os.path.splitext(f)[0]
-
-            try:
-                spec = importlib.util.spec_from_file_location(module_name, module_file)
-                c = importlib.util.module_from_spec(spec)
-                sys.modules[module_name] = c
-                spec.loader.exec_module(c)
-                check = c.Check()
-            except Exception as e:
-                log.error(f"Failed to instantiate check {module_name}. Fix the below:")
-                raise e
-
-            if not isinstance(check, CheckBase):
-                raise Exception(f"Check {module_name} needs to subclass CheckBase!")
+        for module_name, c in _load_check_modules():
+            check = c.Check()
 
             # Ignore checks that only run when checking with a font
             if check.requires_font and not perform_shaping_checks:
@@ -85,9 +105,9 @@ class Checker:
 
             fulfills = True
 
-            if "script" in check.conditions:
-                if "script" in check.conditions:
-                    if check.conditions["script"] != orthography["script"]:
+            if "scripts" in check.conditions:
+                if "scripts" in check.conditions:
+                    if orthography["script"] not in check.conditions["scripts"]:
                         fulfills = False
 
             if fulfills and "attributes" in check.conditions:
@@ -283,15 +303,13 @@ class Checker:
         if orthographies == []:
             return {} if return_script_object else False
 
-        self.shaper = None
-        if shaping:
-            # Setup a reusable shaper to run checks with
+        if shaping and self.shaper is None:
             self.shaper = Shaper(self.fontpath)
 
         for ort in orthographies:
             supported = True
             checks = self._get_checks_for_orthography(
-                orthography=ort, perform_shaping_checks=self.shaper is not None
+                orthography=ort, perform_shaping_checks=shaping
             )
 
             # FIXME TBD Run all checks, even after one has failed, to get
@@ -365,7 +383,6 @@ class FontChecker(Checker):
         super().__init__(fontpath=fontpath)
 
         self.font = TTFont(fontpath, lazy=True)
-        self.shaper = Shaper(fontpath)
         self.characters = self._parse_font_chars()
 
     def get_supported_languages(self, **kwargs):

hyperglot-0.8.1/lib/hyperglot/checks/check_arabic_joining.py → hyperglot-0.8.2/lib/hyperglot/checks/check_joining.py

@@ -23,10 +23,29 @@ class Check(CheckBase):
     The check is only performed for characters with a joining type of D, R, L,
     or T, which require joining behavior which are defined in unicode and
     saved in lib/hyperglot/extra_data/joining-types.yaml
+
+    NOTE: All scripts as retrieved from characters with joining types D, R, L
+    (not T). As these (missing*) scripts are added to Hyperglot (with their
+    Hyperglot spelling/name), opt them in to this check and ideally write some
+    tests to confirm.
+
+    Adlm: Adlam*
+    Arab: Arabic
+    Chrs: Chorasmian*
+    Mand: Mandaic*
+    Mani: Manichaean*
+    Mong: Mongolian*
+    Nkoo: Nko
+    Ougr: Old Uyghur*
+    Phag: Phags Pa*
+    Phlp: Psalter Pahlavi*
+    Rohg: Hanifi Rohingya*
+    Sogd: Sogdian*
+    Syrc: Syriac
     """
 
     conditions = {
-        "script": "Arabic",
+        "scripts": ("Arabic", "N'Ko", "Syriac"),
         "attributes": (
             "base",
             "auxiliary",

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/cli.py

@@ -51,9 +51,10 @@ def validate_font(ctx, param, value):
     Validation method to ensure we can work with the passed in font file
     """
     for v in value:
-        if os.path.splitext(v)[1][1:] not in ["ttf", "otf"]:
+        if os.path.splitext(v)[1][1:] not in ["ttf", "otf", "woff", "woff2"]:
             raise click.BadParameter(
-                "The passed in font file does not appear " "to be of ttf or otf format"
+                "The passed in font file does not appear "
+                "to be of ttf, otf, woff or woff2 format"
             )
 
         try:
@@ -357,7 +358,7 @@ def cli(
     elif verbose > 1:
         # For debugging verbosity also opt in to all near misses reporting
         loglevel = logging.DEBUG
-        logging.getLogger("hyperglot.checks.check_arabic_joining").setLevel(
+        logging.getLogger("hyperglot.checks.check_joining").setLevel(
             logging.DEBUG
         )
         logging.getLogger("hyperglot.checks.check_brahmi_conjuncts").setLevel(
@@ -384,7 +385,7 @@ def cli(
     else:
         loglevel = logging.WARNING
 
-        logging.getLogger("hyperglot.checks.check_arabic_joining").setLevel(loglevel)
+        logging.getLogger("hyperglot.checks.check_joining").setLevel(loglevel)
         logging.getLogger("hyperglot.checks.check_brahmi_conjuncts").setLevel(loglevel)
         logging.getLogger("hyperglot.checks.check_brahmi_halfforms").setLevel(loglevel)
         logging.getLogger("hyperglot.checks.check_combination_marks").setLevel(loglevel)
@@ -418,7 +419,7 @@ def cli(
     logging.getLogger("hyperglot.shaper").setLevel(loglevel)
     logging.getLogger("hyperglot.checker").setLevel(loglevel)
 
-    # Initialize language cache after loggin is configured
+    # Initialize language cache after logging is configured
     from hyperglot.language import _load_language_cache
     _load_language_cache()
 
@@ -591,8 +592,12 @@ def data(search=""):
     hits, msg = find_language(search)
 
     print(msg)
-    for h in hits:
-        print(h.presentation)
+    if hits:
+        for h in hits:
+            print(h.presentation)
+    else:
+        print("Nothing found.")
+        print()
 
 
 @click.command()

hyperglot-0.8.2/lib/hyperglot/data/aoc.yaml

@@ -0,0 +1,20 @@
+contributors:
+- Ana Ribeiro
+name: Pemon
+note: The original submission describes the language as threatened with extinction.
+orthographies:
+- autonym: Përepepɨ/Përe
+  base: A C D E H I Ï J K M N O Ö P R S T U Ü W Y ’ a c d e h i ï j k m n o ö p r s t u ü w y
+  marks: ◌̈
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Ethnologue. (n.d.). *Pemon*. https://www.ethnologue.com/language/aoc/
+- Década Internacional das Línguas Indígenas no Brasil. (n.d.). https://www.decadalinguasindigenasbr.com/
+- Museu do Índio. (n.d.). *Portal Japiim*. https://japiim.museudoindio.gov.br/index.php
+speakers: 900
+status: living
+validity: preliminary

hyperglot-0.8.2/lib/hyperglot/data/atx.yaml

@@ -0,0 +1,22 @@
+contributors:
+- Gabriela Serpa
+name: Arutani
+note: 'Alternative names listed in the original submission: Anake, Aoaqui, Auakê, Auaqué, Awaikê, Awaké, Oewaku, Orotani, Uruak, Urutaní. The source reports 4 speakers in Brazil and 16 in Venezuela; speakers_date was not specified.'
+orthographies:
+- auxiliary: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z À Á Â Ã Ç É Ê Í Ó Ô Õ Ú Ü à á â ã ç é ê í ó ô õ ú ü
+  base: A Á Ã E H I Ĩ K M N Ñ O P R S T U W X Y a á ã e h i ĩ k m n ñ o p r s t u w x y
+  marks: ◌́ ◌̃ ◌̀ ◌̂ ◌̈ ◌̧
+  note: The original submission notes that tilde occurs on all vowels.
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Ethnologue. (n.d.). *Arutani*. https://www.ethnologue.com/language/atx/
+- Endangered Languages Project. (n.d.). *Language search map*. https://www.endangeredlanguages.com/language-search-map
+- Museu do Índio. (n.d.). *Arutani*. Portal Japiim. https://japiim.museudoindio.gov.br/dic/arutani/index.php
+- ScriptSource. (n.d.). *Arutani*. https://scriptsource.org/cms/scripts/page.php?item_id=language_detail&key=atx
+speakers: 20
+status: living
+validity: preliminary

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/data/azb.yaml

@@ -22,7 +22,7 @@ orthographies:
   numerals: <azj>
   punctuation: <azj>
   script: Latin
-  status: primary
+  status: secondary
 sources:
 - Azerbaijani language. (2024, August 24). In *Wikipedia*. https://en.wikipedia.org/wiki/Azerbaijani_language?oldid=1242052519
 speakers: 13823350

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/data/azj.yaml

@@ -9,15 +9,14 @@ orthographies:
   marks: ◌̆
   note: Official in Dagestan (Russia).
   numerals: <default>
-  punctuation: '<default> “ ” " „
-
-    '
+  punctuation: '<default> “ ” " „ '
   script: Cyrillic
-  status: primary
+  status: secondary
 - auxiliary: Ä ä
   base: A B C D E F G H I J K L M N O P Q R S T U V X Y Z Ç Ö Ü Ğ Ş Ə a b c d e f g h i j k l m n o p q r s t u v x y z ç ö ü ğ İ ı ş ə ʼ
   currency: <default> ₼
   marks: ◌̆ ◌̇ ◌̈ ◌̧
+  note: Official national language of Azerbaijan.
   numerals: <default>
   punctuation: <default>
   script: Latin

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/data/eng.yaml

@@ -4,8 +4,8 @@ contributors:
 name: English
 orthographies:
 - autonym: English
-  auxiliary: À Á Ç È É Ê Ë Ï Ñ Ô Ö à á ç è é ê ë ï ñ ô ö
-  base: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Æ Œ a b c d e f g h i j k l m n o p q r s t u v w x y z æ œ
+  auxiliary: À Á Ç È É Ê Ë Ï Ñ Ô Ö Æ Œ à á ç è é ê ë ï ñ ô ö æ œ
+  base: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z
   currency: <default> € $ ¢ £
   marks: ◌̀ ◌́ ◌̂ ◌̃ ◌̈ ◌̧
   numerals: <default>

hyperglot-0.8.2/lib/hyperglot/data/ese.yaml

@@ -0,0 +1,30 @@
+contributors:
+- Denis Moyogo Jacquerye
+- Sergio Martins
+name: Ese Ejja
+note: Vuillermet (2012) cites several orthographies (missionaries, 1995-1996 proposal, 2003-2004 proposal, Peru 2000, and Vuillermet 2012). The main differences are (1) the use of c and qu or k, (2) the use of cu or ku or kw, (3 and 4) the use of jj and j, j and h, or x and j, (5) the use of hu or w. Gallinate and Machuqui (2023) proposed another alphabet, similar to Vuillermet (2012) but with jj instead of x.
+orthographies:
+- autonym: ese ejja
+  auxiliary: X x
+  base: A E I O U B P D T C Q S H J M N Ñ Y a e i o u b p d t c q s h j m n ñ y '
+  marks: ◌̃
+  note: Local orthography used in Bolivia. The ILV and MNT orthography uses b p d t c qu cu s sh jj j ch m n ñ y hu and a e i o.
+  numerals: <default>
+  script: Latin
+  status: primary
+- autonym: ese eja
+  base: A B C D E H I J K M N Ñ O P S T U W Y a b c d e h i j k m n ñ o p s t u w y ’
+  marks: ◌̃
+  note: Local orthography used in Peru. The Peru orthography uses a b ch d ’ e h i j k ku m n ñ o p s sh t ts w y.
+  numerals: <default>
+  script: Latin
+  status: primary
+sources:
+- Gabriel Gallinate and Alejandro Machuqui Dominguez. (2023, 2 July) Acta de Taller de Alfabeto Ese Ejja.
+- Ministerio de Educación del Perú. (2006, September 8) RD No 0683-2006 ED.
+- Ministerio de Educación del Perú. (2015, June 12) RM N° 303-2015 MINEDU. https://www.gob.pe/institucion/minedu/normas-legales/168711-303-2015-minedu
+- Marine Vuillermet. (2012). A Grammar of Ese Ejja, a Takanan language of the Bolivian Amazon.
+- Ese Ejja language. (2024, May 26). In *Wikipedia*. https://en.wikipedia.org/wiki/Ese_Ejja_language?oldid=1225689973
+speakers: 700
+speakers_date: 2007
+validity: draft

hyperglot-0.8.2/lib/hyperglot/data/gae.yaml

@@ -0,0 +1,27 @@
+contributors:
+- Amanda Martins
+name: Warekena (Guarequena)
+note: The original submission reports approximately 10 speakers in Brazil and 200 in Venezuela, describes the language as severely endangered, and identifies alternative names Guarequena, Wanekena, Uarequena, and Baniva de Maroa.
+orthographies:
+- auxiliary: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z À Á Â Ã Ç É Ê Í Ó Ô Õ Ú Ü à á â ã ç é ê í ó ô õ ú ü
+  base: A Ã B D E Ẽ H I Ĩ K L M N O P R S T U Ũ V W X Y a ã b d e ẽ h i ĩ k l m n o p r s t u ũ v w x y
+  marks: ◌̃ ◌̀ ◌́ ◌̂ ◌̈ ◌̧
+  note: The original submission states that there is no widely standardized Warekena orthography and that academic materials use Latin-based phonetic transcriptions influenced by Baniva de Maroa conventions.
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Aikhenvald, A. Y. (2012). *The languages of the Amazon*. Oxford University Press.
+- Aikhenvald, A. Y. (2015). The Arawak language family in the North of Amazonia. In P. Hammarström & H. Haspelmath (Eds.), *Linguistic discovery in the Amazon Basin*. Oxford University Press.
+- Brandão, A. de C. (2014). *Estudo gramatical da língua Warekena (Aruák)* [Doctoral dissertation, Universidade de Brasília]. Repositório da UnB.
+- Endangered Languages Project. (n.d.). *Warekena / Guarequena*. Retrieved October 15, 2025, from https://www.endangeredlanguages.com/lang/3313
+- Glottolog. (2025). *Warekena (ware1252)*. Max Planck Institute for Evolutionary Anthropology. Retrieved October 15, 2025, from https://glottolog.org/resource/languoid/id/ware1252
+- Mosonyi, E., & Camico, C. (1996). *Propuesta de ortografía práctica para el idioma Baniva (Arawak del Orinoco)*. Instituto Caribe de Antropología y Sociología.
+- Native Languages of the Americas. (n.d.). *Guarequena language (Warekena, Baniva de Maroa)*. Retrieved October 15, 2025, from https://www.native-languages.org/guarequena.htm
+- UNESCO. (2010). *Atlas of the world’s languages in danger* (3rd ed.). UNESCO Publishing.
+- '*Língua baniva de Maroa*. (2024, October 17). In *Wikipédia*. https://pt.wikipedia.org/w/index.php?title=Língua_baniva_de_Maroa&oldid=68838306'
+speakers: 210
+status: living
+validity: preliminary

hyperglot-0.8.2/lib/hyperglot/data/gta.yaml

@@ -0,0 +1,22 @@
+contributors:
+- Giovanna Julião
+name: Guató
+note: The original submission notes recent language revitalization efforts, particularly cultural projects and the introduction of Guató into activities at the Indigenous school.
+orthographies:
+- auxiliary: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z À Á Â Ã Ç É Ê Í Ó Ô Õ Ú Ü à á â ã ç é ê í ó ô õ ú ü
+  base: A Ã B D E Ẽ F G H I Ĩ J K M N O P R T U Ũ V W X Y Ỹ a ã b d e ẽ f g h i ĩ j k m n o p r t u ũ v w x y ỹ
+  marks: ◌̃ ◌̀ ◌́ ◌̂ ◌̈ ◌̧
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Ethnologue. (n.d.). *Guató*. https://www.ethnologue.com/language/gta/
+- Instituto Socioambiental. (n.d.). *Guató*. Povos Indígenas no Brasil. https://pib.socioambiental.org/pt/Povo:Guat%C3%B3
+- Glottolog. (n.d.). *Guató (guat1253)*. https://glottolog.org/resource/languoid/id/guat1253
+- Museu do Índio. (n.d.). *Portal Japiim*. https://japiim.museudoindio.gov.br/index.php
+speakers: 5
+speakers_date: 2008
+status: living
+validity: preliminary

hyperglot-0.8.2/lib/hyperglot/data/gun.yaml

@@ -0,0 +1,23 @@
+contributors:
+- Lauane da Silva Sousa
+name: Guarani Mbyá
+note: The original submission dates the speaker estimate to 2007–2008.
+orthographies:
+- autonym: Mbyá Ayvu ou Nhandeayvu
+  base: A B E H J K M N O T X Y a b e h j k m n o t x y
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Ethnologue. (n.d.). *Mbyá Guaraní*. https://www.ethnologue.com/language/gun/
+- Glottolog. (n.d.). *Mbyá Guaraní*. https://glottolog.org/resource/languoid/id/mbya1239
+- Museu do Índio. (n.d.). *Portal Japiim*. https://japiim.museudoindio.gov.br/
+- Brasil de Fato. (n.d.). [Source cited in the original submission].
+- Instituto Socioambiental. (n.d.). *Povos Indígenas no Brasil*. https://pib.socioambiental.org/
+- Brazil1500.tripod.com. (n.d.). [Source cited in the original submission].
+- '*Mbyá Guaraní language*. (2026, August 1). In *Wikipedia*. https://en.wikipedia.org/w/index.php?title=Mbyá_Guaraní_language&oldid=1367164941'
+speakers: 15050
+status: living
+validity: preliminary

hyperglot-0.8.2/lib/hyperglot/data/ite.yaml

@@ -0,0 +1,23 @@
+contributors:
+- Diogo Alves
+name: Itene
+note: The original submission describes Itene / Moré-Kuyubim as a Chapacuran language spoken by Moré and Kuyubim communities near the Bolivia–Brazil border, with a Latin-based orthography and critically reduced speaker population.
+orthographies:
+- auxiliary: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z À Á Â Ã Ç É Ê Í Ó Ô Õ Ú Ü à á â ã ç é ê í ó ô õ ú ü
+  base: A E F I K M N Ñ O P R S T U W X Y Z ' a e f i k m n ñ o p r s t u w x y z
+  marks: ◌̃ ◌̀ ◌́ ◌̂ ◌̈ ◌̧
+  script: Latin
+  status: primary
+preferred_name: Moré-Kuyubim
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Angenot-de Lima, G. (2002). *Descrição fonológica, gramatical e lexical do moré, língua amazônica da Bolívia e do Brasil* [Doctoral dissertation, Leiden University]. Etnolinguistica.org. http://etnolinguistica.wdfiles.com/local--files/tese%3Alima-2002/lima_2002_tomo1.pdf
+- Endangered Languages Archive. (2020). *Documentation of Moré (Iténez), a Chapacuran language of Bolivia and Brazil*. https://www.elararchive.org/dk0833
+- Museu do Índio. (n.d.). *Dicionário Moré-Kuyubim*. Portal Japiim. https://japiim.museudoindio.gov.br/dic/morekuyubim/index.php
+- Hammarström, H., Forkel, R., Haspelmath, M., & Bank, S. (Eds.). (2025). *Moré (Iténez)*. Glottolog 5.0. Max Planck Institute for Evolutionary Anthropology. https://glottolog.org/resource/languoid/id/iten1243
+speakers: 20
+speakers_date: 2025
+status: living
+validity: preliminary

hyperglot-0.8.2/lib/hyperglot/data/kpj.yaml

@@ -0,0 +1,26 @@
+autonym: Iny rybè
+contributors:
+- Maria Fernanda Paz Almeida
+name: Karajá
+note: The original submission states that the data refer specifically to Karajá proper, excluding varieties such as Javaé and Northern Karajá.
+orthographies:
+- auxiliary: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z a b c d e f g h i j k l m n o p q r s t u v w x y z À Á Â Ã Ç É Ê Í Ó Ô Õ Ú Ü à á â ã ç é ê í ó ô õ ú ü
+  base: A B D E H I Ĩ J K L M N O R S T U W X Y À Ã È Ò Õ Ỹ a b d e h i ĩ j k l m n o r s t u x w y à ã è ò õ ỹ
+  marks: ◌̃ ◌̀ ◌́ ◌̂ ◌̈ ◌̧
+  script: Latin
+  status: primary
+reviewers:
+- Rafael Dietzsch
+- Thiago Chacon
+sources:
+- Instituto Socioambiental. (n.d.). *Karajá*. Povos Indígenas no Brasil. https://pib.socioambiental.org/pt/Povo:Iny_Karaj%C3%A1
+- Endangered Languages Project. (n.d.). *Karajá*. https://www.endangeredlanguages.com/pt-br/node/89499
+- 'Crevels, M. (2012). Language endangerment in South America: The clock is ticking. In L. Campbell & V. Grondona (Eds.), *The Indigenous Languages of South America: A Comprehensive Guide* (pp. 167–234). Mouton de Gruyter.'
+- Museu do Índio. (n.d.). *Karajá*. Portal Japiim / ProDoclin. https://japiim.museudoindio.gov.br/dic/karaja/index.php
+- Projeto de Documentação da Língua Karajá. (2011, March 10). *Relatório com o perfil tipológico da língua Karajá* (Projeto 914BRA4010). Museu do Índio / FUNAI / UNESCO.
+- Ethnologue. (n.d.). *Karajá*. https://www.ethnologue.com/language/kpj/
+- 'Instituto Brasileiro de Geografia e Estatística. (2012). *Censo demográfico 2010: Características gerais dos indígenas: Resultados do universo*. IBGE.'
+speakers: 2137
+speakers_date: 2010
+status: living
+validity: preliminary

{hyperglot-0.8.1 → hyperglot-0.8.2}/lib/hyperglot/data/mcf.yaml

@@ -2,13 +2,13 @@ contributors:
 - Sergio Martins
 name: Matsés
 orthographies:
-- base: A B C E G H I J L M N O P Q R S T U Y Ā Ē Ī Ō Ū a b c e g h i j l m n o p q r s t u y ' ā ē ī ō ū
-  marks: ◌̄
+- base: A B C E G H I J L M N O P Q R S T U Y Ä Ë Ï Ö Ü CH SH TS AN EN ËN IN ON UN a b c e g h i j l m n o p q r s t u y ' Ch Sh Ts An En Ën In On Un  ä ë ï ö ü ch sh ts an en ën in on un
+  marks: ◌̈
   numerals: <default>
   script: Latin
   status: primary
 sources:
-- Ager, S. (2021, May 4). *Omniglot* https://www.omniglot.com
+- Ager, S. (2021, May 4). *Omniglot* https://www.omniglot.com/writing/matses.htm
 - Matsés language. (2024, March 26). In *Wikipedia*. https://en.wikipedia.org/wiki/Mats%C3%A9s_language?oldid=1215640765
 speakers: 2200
 speakers_date: 2006