Ignore commas and periods across all grammars

Author: rlskoeser

src/undate/converters/calendars/hebrew/parser.py

@@ -4,6 +4,7 @@
 
 grammar_path = GRAMMAR_FILE_PATH / "hebrew.lark"
 
-with open(grammar_path) as grammar:
-    # NOTE: LALR parser is faster but can't be used to ambiguity between years and dates
-    hebrew_parser = Lark(grammar.read(), start="hebrew_date", strict=True)
+# open based on filename to allow relative imports based on grammar file
+hebrew_parser = Lark.open(
+    str(grammar_path), rel_to=__file__, start="hebrew_date", strict=True
+)

src/undate/converters/calendars/islamic/parser.py

@@ -4,6 +4,7 @@
 
 grammar_path = GRAMMAR_FILE_PATH / "islamic.lark"
 
-with open(grammar_path) as grammar:
-    # NOTE: LALR parser is faster but can't be used due to ambiguity between years and days
-    islamic_parser = Lark(grammar.read(), start="islamic_date", strict=True)
+# open based on filename to allow relative imports based on grammar file
+islamic_parser = Lark.open(
+    str(grammar_path), rel_to=__file__, start="islamic_date", strict=True
+)

src/undate/converters/grammars/combined.lark

@@ -1,10 +1,9 @@
 %import common.WS
 %ignore WS
 
-// Some abbreviations use periods; some default date formats
-// include commas. Ignore both. (Copied from gregorian.lark)
-PUNCTUATION: "." | ","
-%ignore PUNCTUATION
+// Ignore periods and commas in dates
+%import .undate_common.DATE_PUNCTUATION
+%ignore DATE_PUNCTUATION
 
 start: (edtf__start | hebrew__hebrew_date  | islamic__islamic_date | gregorian__gregorian_date )
 

src/undate/converters/grammars/gregorian.lark

@@ -1,10 +1,9 @@
 %import common.WS
 %ignore WS
 
-// Some abbreviations use periods; some default date formats
-// include commas. Ignore both
-PUNCTUATION: "." | ","
-%ignore PUNCTUATION
+// Ignore periods and commas in dates
+%import .undate_common.DATE_PUNCTUATION
+%ignore DATE_PUNCTUATION
 
 %import .gregorian_multilang (month_1, month_2, month_3, month_4, month_5,  \
 	month_6, month_7, month_8, month_9, month_10, month_11, month_12)

src/undate/converters/grammars/hebrew.lark

@@ -1,9 +1,13 @@
 %import common.WS
 %ignore WS
 
+// Ignore periods and commas in dates
+%import .undate_common.DATE_PUNCTUATION
+%ignore DATE_PUNCTUATION
+
 // only support day month year format for now
 // parser requires numeric day and year to be distinguished based on order
-hebrew_date: weekday? day month comma? year | month year | year
+hebrew_date: weekday? day month year | month year | year
 
 // TODO: handle date ranges?
 
@@ -31,8 +35,7 @@ month: month_1
 // months have 29 or 30 days; we do not expect leading zeroes
 day: /[1-9]/ | /[12][0-9]/ | /30/
 
-comma: ","
-weekday: ("Monday" | "Tuesday" | "Wednesday" | "Thursday" | "Friday" | "Saturday" | "Sunday") comma?
+weekday: ("Monday" | "Tuesday" | "Wednesday" | "Thursday" | "Friday" | "Saturday" | "Sunday")
 
 
 // months, in order; from convertdate list

src/undate/converters/grammars/islamic.lark

@@ -1,6 +1,10 @@
 %import common.WS
 %ignore WS
 
+// Ignore periods and commas in dates
+%import .undate_common.DATE_PUNCTUATION
+%ignore DATE_PUNCTUATION
+
 // only support day month year format for now
 // parser requires numeric day and year to be distinguished based on order
 islamic_date: weekday? day month year | month year | year