Merge

Procfile

@@ -14,3 +14,5 @@ cwdeng: ./cwdeng-manage runserver
 srseng: ./srseng-manage runserver
 hdneng: ./hdneng-manage runserver
 lacombe:  ./crkLacombeeng-manage runserver
+blaeng: ./blaeng-manage runserver
+

blaeng-manage

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+"""
+Command-line utility for administrative tasks.
+"""
+
+import os
+import sys
+from pathlib import Path
+
+# sys.path[0] is initialized to the directory containing the script, which
+# isn’t right for our purposes.
+sys.path[0] = os.fspath(Path(sys.path[0]) / "src")
+
+if __name__ == "__main__":
+    os.environ.setdefault("DJANGO_SETTINGS_MODULE", "blaeng.site.settings")
+
+    from django.core.management import execute_from_command_line
+
+    execute_from_command_line(sys.argv)

docs/developers-guide.md

@@ -221,6 +221,7 @@ Then you can access the dictionary applications at various port numbers:
  - arpeng: <http://127.0.0.1:8007/>
  - cwdeng: <http://127.0.0.1:8005/>
  - srseng: <http://127.0.0.1:8009/>
+ - blaeng: <http://127.0.0.1:8011/>
 
 Because [cookies are not port-specific for historical insecurity
 reasons](https://stackoverflow.com/questions/1612177/are-http-cookies-port-specific),
@@ -232,6 +233,7 @@ adding the following to `/etc/hosts`:
     127.0.0.1 cwdeng-local
     127.0.0.1 crkeng-local
     127.0.0.1 srseng-local
+    127.0.0.1 blaeng-local
 
 Then you can access the sites with cookie isolation at
 <http://crkeng-local:8000/>, <http://cwdeng-local:8005/>,

scripts/dev-bootstrap

@@ -20,6 +20,7 @@ for LANG_PAIR in \
     crkeng \
     cwdeng \
     srseng \
+    blaeng \
 ; do
     for USE_TEST_DB in true false; do
         export USE_TEST_DB

src/CreeDictionary/API/search/presentation.py

@@ -56,9 +56,9 @@ class _InitialChangeResult(AbstractResult):
 @dataclass
 class _LexicalEntry:
     entry: List[_ReduplicationResult | SerializedWordform | _InitialChangeResult]
-    text: str
+    text: Optional[str]
     url: str
-    id: str
+    id: str | int | None
     type: LexicalEntryType
     original_tag: FSTTag
 
@@ -173,9 +173,10 @@ def __init__(
             show_emoji=self._show_emoji,
         )
 
-        self.preverbs = [
-            lexical_entry["entry"]
+        self.preverbs: List[SerializedWordform] = [
+            cast(SerializedWordform, entry)
             for lexical_entry in self.lexical_info
+            for entry in lexical_entry["entry"]
             if lexical_entry["type"] == "Preverb"
         ]
         self.reduplication = [
@@ -453,22 +454,20 @@ def get_lexical_info(
     animate_emoji: str,
     show_emoji: str,
     dict_source: list,
-) -> List:
+) -> List[dict]:
     if not result_analysis:
         return []
 
     result_analysis_tags = result_analysis.prefix_tags
     first_letters = extract_first_letters(result_analysis)
 
-    lexical_info: List = []
+    lexical_info: List[_LexicalEntry] = []
 
     for i, tag in enumerate(result_analysis_tags):
         preverb_result: Optional[Preverb] = None
         reduplication_string: Optional[str] = None
         _type: Optional[LexicalEntryType] = None
-        entry: Optional[
-            _ReduplicationResult | SerializedWordform | _InitialChangeResult
-        ] = None
+        entry = None
 
         if tag in ["RdplW+", "RdplS+"]:
             reduplication_string = generate_reduplication_string(
@@ -501,16 +500,16 @@ def get_lexical_info(
                                 entries.append(entry)
                 url = "search?q=" + preverb_text
                 _type = "Preverb"
-                id = entries[0]["id"]
+                id: Optional[int] = entries[0]["id"]
                 result = _LexicalEntry(
-                    entry=entries,
+                    entry=cast(Any, entries),
                     text=preverb_text,
                     url=url,
                     id=id,
                     type=_type,
                     original_tag=tag,
                 )
-                lexical_info.append(serialize_lexical_entry(result))
+                lexical_info.append(result)
             else:
                 # Can't find a match for the preverb in the database.
                 # This happens when searching against the test database for
@@ -548,8 +547,8 @@ def get_lexical_info(
                 type=_type,
                 original_tag=tag,
             )
-            lexical_info.append(serialize_lexical_entry(result))
-    return lexical_info
+            lexical_info.append(result)
+    return [serialize_lexical_entry(entry) for entry in lexical_info]
 
 
 def extract_first_letters(analysis: RichAnalysis) -> List[str]:

src/CreeDictionary/search_quality/analyze_results.py

@@ -130,7 +130,7 @@ def load_results_file(results_file: PathLike) -> SampleSearchResultsJson:
         return search_results
 
 
-def analyze(results_file, sample_definition: SampleDefinition = None):
+def analyze(results_file, sample_definition: SampleDefinition = []):
     """
 
     If sample_definition is None, the default will be used.

src/CreeDictionary/tests/API_tests/model_test.py

@@ -227,7 +227,7 @@ def test_search_words_with_reduplication():
     search_result = results.pop()
 
     assert len(search_result.lexical_info) == 1
-    assert search_result.lexical_info[0]["entry"]["text"] == "na-"
+    assert search_result.lexical_info[0]["entry"][0]["text"] == "na-"
     assert search_result.lexical_info[0]["type"] == "Reduplication"
 
 
@@ -241,7 +241,7 @@ def test_search_words_with_inital_change():
     search_result = results.pop()
 
     assert len(search_result.lexical_info) == 1
-    assert search_result.lexical_info[0]["entry"]["text"] == " "
+    assert search_result.lexical_info[0]["entry"][0]["text"] == " "
     assert search_result.lexical_info[0]["type"] == "Initial Change"
 
 

src/blaeng/README.md

@@ -0,0 +1,64 @@
+# Generating a new site from scratch
+
+These are all the instructions I followed to create this new version.
+
+```
+./crkeng-manage newdictsite --port 8011 -v 2 bla eng
+# Add blaeng to morphodict/src/conftest.py
+# Add MORPHODICT_LANGUAGE_ENDONYM to src/blaeng/site/settings.py
+# Add many other details, copying from Woods Cree settings.py, including:
+# MD_SOURCE_LANGUAGE_NAME MD_SOURCE_LANGUAGE_SHORT_NAME MD_ORTHOGRAPHY MD_DICTIONARY_NAME
+./blaeng-manage migrate
+./blaeng-manage ensurecypressadminuser --superuser
+./blaeng-manage ensuretestdb
+# MISSING TRANSDUCERS 
+
+```
+
+I had to make transducers. Generating from the instructions we just collected today!
+
+`git clone giellalt/lang-bla`
+after generating the FSTs with the default infrastructure:
+```
+hfst-xfst
+```
+And ran:
+```
+read lexc src/fst/morphology/lexicon.lexc
+define Morphology
+source src/fst/bla-phonology.xfscript
+define Phonology
+regex ~[ $[ "+Err/Frag" ]];
+define removeFragments
+
+regex ~[ $[ "+Err/Orth" ]];
+define removeNonStandardForms
+regex $[ "+N" | "+V" | "+Ipc" | "+Pron" ];
+define selectDictPOS
+set flag-is-epsilon ON
+regex [ selectDictPOS .o. removeNonStandardForms .o. removeFragments .o. Morphology .o. Phonology ];
+save stack generator-gt-dict-norm.hfst
+define NormativeGenerator
+regex [ [ "<" | ">" | "/" ] -> 0 ];
+define removeBoundaries
+load src/fst/orthography/spellrelax.compose.hfst
+define SpellRelax
+regex [ selectDictPOS .o. removeFragments .o. Morphology .o. Phonology .o. removeBoundaries .o. SpellRelax ];
+# regex [ NormativeGenerator .o. removeBoundaries .o. SpellRelax ];
+invert net
+save stack analyser-gt-dict-desc.hfst
+define DescriptiveAnalyser
+```
+
+
+And then we create the `hfstol` files with:
+
+```
+hfst-fst2fst -O -i INPUT.hfst -o OUTPUT.hfstol
+```
+
+After this, `./blaeng-manage ensuretestdb` works.
+
+```
+./blaeng-manage importjsondict src/blaeng/resources/dictionary/blaeng_test_db.importjson
+```

src/blaeng/site/settings.py

@@ -0,0 +1,58 @@
+"""
+Django settings for blaeng.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.2/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/3.2/ref/settings/
+"""
+
+from pathlib import Path
+
+from morphodict.site import base_dir_setup
+
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+base_dir_setup.set_base_dir(BASE_DIR)
+
+from morphodict.site.settings import *
+
+# Where this application should be deployed:
+PRODUCTION_HOST = "blaeng.altlab.dev"
+
+ALLOWED_HOSTS.append(PRODUCTION_HOST)
+
+DEFAULT_RUNSERVER_PORT = 8011
+
+INSTALLED_APPS.insert(0, "blaeng.app")
+
+# Morphodict configuration
+
+# The ISO 639-1 code is used in the lang="" attributes in HTML.
+MORPHODICT_ISO_639_1_CODE = "bla"
+
+MORPHODICT_SOURCE_LANGUAGE = "bla"
+MORPHODICT_TARGET_LANGUAGE = "eng"
+
+MORPHODICT_SOURCE_LANGUAGE_NAME = "Blackfoot"
+MORPHODICT_SOURCE_LANGUAGE_SHORT_NAME = "Blackfoot"
+
+MORPHODICT_LANGUAGE_ENDONYM = "ᓱᖽᐧᖿ"
+
+MORPHODICT_DICTIONARY_NAME = "sínaakia’tsis"
+
+RELAXED_ANALYZER_FST_FILENAME = "analyser-gt-dict-desc.hfstol"
+STRICT_ANALYZER_FST_FILENAME = RELAXED_ANALYZER_FST_FILENAME
+STRICT_GENERATOR_FST_FILENAME = "generator-gt-dict-norm.hfstol"
+
+MORPHODICT_ORTHOGRAPHY = {
+    "default": "Latn",
+    "available": {
+        "Latn": {"name": "Latin"},
+        "Cans": {
+            "name": "Syllabics",
+            "converter": "CreeDictionary.CreeDictionary.orthography.to_syllabics",
+            },
+    },
+}

src/conftest.py

@@ -9,4 +9,5 @@
     "hdneng/site/settings.py",
     "srseng/site/settings.py",
     "srseng/site/settings_mobile.py",
+    "blaeng/site/settings.py",
 ]