add punctuation to grc (#11426)

* add punctuation to grc

Add support for special editorial punctuation that is common in ancient Greek texts.  Ancient Greek texts, as found in digital and print form, have been largely edited by scholars. Restorations and improvements are normally marked with special characters that need to be handled properly by the tokenizer.

* add unit tests

* simplify regex

* move generic quotes to char classes

* rename unit test

* fix regex

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

Co-authored-by: svlandeg <svlandeg@github.com>
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

spacy/lang/char_classes.py

@@ -280,7 +280,7 @@ _currency = (
 _punct = (
     r"… …… , : ; \! \? ¿ ؟ ¡ \( \) \[ \] \{ \} < > _ # \* & 。 ？ ！ ， 、 ； ： ～ · । ، ۔ ؛ ٪"
 )
-_quotes = r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉'
+_quotes = r'\' " ” “ ` ‘ ´ ’ ‚ , „ » « 「 」 『 』 （ ） 〔 〕 【 】 《 》 〈 〉 〈 〉  ⟦ ⟧'
 _hyphens = "- – — -- --- —— ~"
 
 # Various symbols like dingbats, but also emoji

spacy/lang/grc/__init__.py

@@ -1,11 +1,15 @@
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
+from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
 from ...language import Language, BaseDefaults
 
 
 class AncientGreekDefaults(BaseDefaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    prefixes = TOKENIZER_PREFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    infixes = TOKENIZER_INFIXES
     lex_attr_getters = LEX_ATTRS
     stop_words = STOP_WORDS
 

spacy/lang/grc/punctuation.py

@@ -0,0 +1,46 @@
+from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
+from ..char_classes import LIST_ICONS, ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS
+from ..char_classes import CONCAT_QUOTES
+
+_prefixes = (
+    [
+        "†",
+        "⸏",
+    ]
+    + LIST_PUNCT
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_CURRENCY
+    + LIST_ICONS
+)
+
+_suffixes = (
+    LIST_PUNCT
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_ICONS
+    + [
+        "†",
+        "⸎",
+        r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]",
+    ]
+)
+
+_infixes = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])[+\-\*^](?=[0-9-])",
+        r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
+            al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
+        ),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
+        r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
+        r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])—",
+    ]
+)
+
+TOKENIZER_PREFIXES = _prefixes
+TOKENIZER_SUFFIXES = _suffixes
+TOKENIZER_INFIXES = _infixes

spacy/tests/lang/grc/test_tokenizer.py

@@ -0,0 +1,18 @@
+import pytest
+
+
+# fmt: off
+GRC_TOKEN_EXCEPTION_TESTS = [
+    ("τὸ 〈τῆς〉 φιλοσοφίας ἔργον ἔνιοί φασιν ἀπὸ ⟦βαρβάρων⟧ ἄρξαι.", ["τὸ", "〈", "τῆς", "〉", "φιλοσοφίας", "ἔργον", "ἔνιοί", "φασιν", "ἀπὸ", "⟦", "βαρβάρων", "⟧", "ἄρξαι", "."]),
+    ("τὴν δὲ τῶν Αἰγυπτίων φιλοσοφίαν εἶναι τοιαύτην περί τε †θεῶν† καὶ ὑπὲρ δικαιοσύνης.", ["τὴν", "δὲ", "τῶν", "Αἰγυπτίων", "φιλοσοφίαν", "εἶναι", "τοιαύτην", "περί", "τε", "†", "θεῶν", "†", "καὶ", "ὑπὲρ", "δικαιοσύνης", "."]),
+    ("⸏πόσις δ' Ἐρεχθεύς ἐστί μοι σεσωσμένος⸏", ["⸏", "πόσις", "δ'", "Ἐρεχθεύς", "ἐστί", "μοι", "σεσωσμένος", "⸏"]),
+    ("⸏ὔπνον ἴδωμεν⸎", ["⸏", "ὔπνον", "ἴδωμεν", "⸎"]),
+]
+# fmt: on
+
+
+@pytest.mark.parametrize("text,expected_tokens", GRC_TOKEN_EXCEPTION_TESTS)
+def test_grc_tokenizer(grc_tokenizer, text, expected_tokens):
+    tokens = grc_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert expected_tokens == token_list