v1.20.5 Improve date inferring

frictionlessdata · Mar 12, 2024 · c81eb66 · c81eb66
1 parent 5e9d7f6
commit c81eb66
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 12 deletions.
diff --git a/tableschema/VERSION b/tableschema/VERSION
@@ -1 +1 @@
-1.20.4
+1.20.5
diff --git a/tableschema/schema.py b/tableschema/schema.py
@@ -550,7 +550,7 @@ def __hash__(self):
     'array',
     'datetime',
     'time',
-    'date',
+    ('date', ('%Y-%m-%d', '%Y/%m/%d', '%d/%m/%Y', '%m/%d/%Y', '%Y%m%d', '%Y.%m.%d')),
     'integer',
     'number',
     'boolean',
@@ -569,12 +569,17 @@ def __init__(self, missing_values):
         self.missing_values = missing_values
 
     def cast(self, value):
-        for priority, name in enumerate(_INFER_TYPE_ORDER):
+        for priority, type_rec in enumerate(_INFER_TYPE_ORDER):
+            if isinstance(type_rec, tuple):
+                name, formats = type_rec
+            else:
+                name, formats = type_rec, ['default']
             cast = getattr(types, 'cast_%s' % name)
             if value not in self.missing_values:
-                result = cast('default', value)
-                if result != config.ERROR:
-                    yield (name, 'default', priority)
+                for format in formats:
+                    result = cast(format, value)
+                    if result != config.ERROR:
+                        yield (name, format, priority)
 
 
 class _TypeResolver(object):

diff --git a/tests/test_schema.py b/tests/test_schema.py
@@ -309,19 +309,21 @@ def test_save(tmpdir, apply_defaults):
 
 def test_infer():
     data = [
-      ['id', 'age', 'name'],
-      ['1','39','Paul'],
-      ['2','23','Jimmy'],
-      ['3','36','Jane'],
-      ['4','N/A','Judy'],
+      ['id', 'age', 'name', 'dob'],
+      ['1','39','Paul','28/1/1979'],
+      ['2','23','Jimmy','13/6/1995'],
+      ['3','36','Jane','17/9/1980'],
+      ['4','N/A','Judy','19/4/1983'],
     ]
     schema = Schema()
     schema.infer(data)
     assert schema.descriptor == {
         'fields': [
             {'format': 'default', 'name': 'id', 'type': 'integer'},
             {'format': 'default', 'name': 'age', 'type': 'integer'},
-            {'format': 'default', 'name': 'name', 'type': 'string'}],
+            {'format': 'default', 'name': 'name', 'type': 'string'},
+            {'format': '%d/%m/%Y', 'name': 'dob', 'type': 'date'},
+        ],
         'missingValues': ['']}
     data = [
       ['id', 'age', 'name'],