Merge pull request #122 from roedoejet/master

Release

.travis.yml

@@ -15,12 +15,15 @@ before_install:
 install:
   # Install Python dependencies
   - pip3 install -r /home/travis/build/roedoejet/g2p/requirements.txt
+  # Install g2p
+  - cd /home/travis/build/roedoejet/g2p && pip3 install -e .
+  # Legal check: make sure we don't introduce GPL dependencies
+  - pip3 install pip-licenses
+  - if pip-licenses | grep -v 'Artistic License' | grep -v LGPL | grep GNU; then echo 'Please avoid introducing *GPL dependencies'; false; fi
   # Install testing requirements
   - pip3 install coverage
   - pip3 install coveralls
   - pip3 install gunicorn
-  # Install g2p
-  - cd /home/travis/build/roedoejet/g2p && pip3 install -e .
 
 before_script:
   - gunicorn --worker-class eventlet -w 1 g2p.app:APP --no-sendfile --bind 0.0.0.0:5000 --daemon

g2p/api.py

@@ -125,7 +125,7 @@ def update_docs():
     LOGGER.info('Updated API documentation')
 
 
-g2p_api = Blueprint('resources.g2p', __name__)
+g2p_api = Blueprint('resources-g2p', __name__)
 
 CORS(g2p_api)
 

g2p/cli.py

@@ -316,7 +316,7 @@ def scan(lang, path):
     pattern = "[^" + mapped_string + filter_chars + ".]"
     prog = re.compile(pattern)
 
-    with open(path, "r") as file:
+    with open(path, "r", encoding="utf8") as file:
         data = normalize(file.read(), "NFD")
         if not case_sensitive:
             data = data.lower()

g2p/mappings/__init__.py

@@ -77,7 +77,7 @@ def __init__(self, mapping=None, abbreviations: Union[str, DefaultDict[str, List
         # yes, they should
         self.allowable_kwargs = ['language_name', 'display_name', 'mapping', 'in_lang',
                                  'out_lang', 'out_delimiter', 'as_is', 'case_sensitive', 'rule_ordering',
-                                 'escape_special', 'norm_form', 'prevent_feeding', 'reverse']
+                                 'escape_special', 'norm_form', 'prevent_feeding', 'reverse', 'type']
         self.kwargs = OrderedDict(kwargs)
         self.processed = False
         if isinstance(abbreviations, defaultdict) or not abbreviations:
@@ -101,6 +101,8 @@ def __init__(self, mapping=None, abbreviations: Union[str, DefaultDict[str, List
             elif 'id' in self.kwargs:
                 loaded_config = self.find_mapping_by_id(self.kwargs['id'])
                 self.process_loaded_config(loaded_config)
+            elif self.kwargs.get("type", "") == "unidecode":
+                self.mapping = []
             else:
                 raise exceptions.MalformedLookup()
         if self.abbreviations:
@@ -182,10 +184,13 @@ def process_loaded_config(self, config):
         ''' For a mapping loaded from a file, take the keyword arguments and supply them to the
             Mapping, and get any abbreviations data.
         '''
-        self.mapping = config['mapping_data']
+        if config.get("type", "") == "unidecode":
+            self.mapping = []
+        else:
+            self.mapping = config['mapping_data']
+            self.abbreviations = config.get('abbreviations_data', None)
         mapping_kwargs = OrderedDict(
             {k: v for k, v in config.items() if k in self.allowable_kwargs})
-        self.abbreviations = config.get('abbreviations_data', None)
         # Merge kwargs, but prioritize kwargs that initialized the Mapping
         self.kwargs = {**mapping_kwargs, **self.kwargs}
 

g2p/mappings/create_fallback_mapping.py

@@ -1,6 +1,6 @@
 import os
 
-from unidecode import unidecode
+from text_unidecode import unidecode
 
 from g2p import make_g2p
 from g2p.log import LOGGER

g2p/mappings/langs/generated/config.yaml

@@ -132,15 +132,16 @@ mappings:
   - authors:
       - Generated 2020-09-18 10:40:15.289530
       - Updated by hand 2021-02-10 Eric Joanis to handle ejectives
+      - Update by hand 2021-05-21 Shankhalika Srikanth reorder rules with aspiration
     case_sensitive: false
     display_name: Tlingit IPA to English IPA
     escape_special: false
     in_lang: tli-ipa
     language_name: Tlingit IPA
-    mapping: tli-norm-ipa_to_eng-ipa.json
-    norm_form: NFC
+    mapping: tli-ipa_to_eng-ipa.json
+    norm_form: NFD
     out_lang: eng-ipa
-    prevent_feeding: false
+    prevent_feeding: true
     reverse: false
     rule_ordering: as-written
   - authors:
@@ -235,7 +236,7 @@ mappings:
     reverse: false
     rule_ordering: as-written
   - authors:
-      - Generated 2021-03-24 21:42:30.002668
+      - Generated 2021-08-01 19:37:38.316339
     case_sensitive: false
     display_name: tau-ipa IPA to eng-ipa IPA
     escape_special: false
@@ -244,7 +245,7 @@ mappings:
     mapping: tau-ipa_to_eng-ipa.json
     norm_form: NFD
     out_lang: eng-ipa
-    prevent_feeding: true
+    prevent_feeding: false
     reverse: false
     rule_ordering: as-written
   - authors:

g2p/mappings/langs/generated/haa-ipa_to_eng-ipa.json

@@ -1,4 +1,40 @@
 [
+    {
+        "in": "\u0303\u0300",
+        "out": "\u0303",
+        "context_before": "",
+        "context_after": ""
+    },
+    {
+        "in": "\u0303\u030C",
+        "out": "\u0303",
+        "context_before": "",
+        "context_after": ""
+    },
+    {
+        "in": "\u0303\u0302",
+        "out": "\u0303",
+        "context_before": "",
+        "context_after": ""
+    },
+    {
+        "in": "\u0300",
+        "out": "",
+        "context_before": "",
+        "context_after": ""
+    },
+    {
+        "in": "\u030C",
+        "out": "",
+        "context_before": "",
+        "context_after": ""
+    },
+    {
+        "in": "\u0302",
+        "out": "",
+        "context_before": "",
+        "context_after": ""
+    },
     {
         "in": "\u207fk",
         "out": "nk",
@@ -347,12 +383,6 @@
         "context_before": "",
         "context_after": ""
     },
-    {
-        "in": "\u0303",
-        "out": "",
-        "context_before": "",
-        "context_after": ""
-    },
     {
         "in": "\u0259",
         "out": "\u0259",