Textminer normal mode

.gitignore

@@ -58,4 +58,6 @@ docs/_build/
 
 # PyBuilder
 target/
-
+.direnv/
+.idea/
+.envrc

textminer/separator.py

@@ -0,0 +1,61 @@
+import re
+
+def words(txt):
+    match = re.findall(r"\b[\d]*[A-Za-z-]+", txt)
+    if match:
+        return match
+
+def phone_number(num):
+    match = re.match(r"\(?(?P<area_code>\d{3})[\.\)]?[.\- ]?(?P<first>\d{3})[.\-]?(?P<last>\d{4})", num)
+    if match:
+        temp_dict = match.groupdict()
+        phone_dict = {}
+        phone_dict["area_code"] = "{area_code}".format(**temp_dict)
+        phone_dict["number"] = "{first}-{last}".format(**temp_dict)
+        return phone_dict
+
+def zipcode(num):
+    match = re.match(r"""(?P<zip>\d{5}) #five digit zipcode
+                    (-(?P<plus4>\d{4}) #can also have dash
+                    | #or
+                    $ #has to end, no more number allowed
+                    )""", num, re.VERBOSE)
+    if match:
+        return match.groupdict()
+
+
+def dates(num):
+    match = re.match(r"""\A(?P<year>\d{4}) # YYYY
+                    [/-]
+                    (?P<month>\d{1,2}) #MM
+                    [/-]
+                    (?P<day>\d{2}) #DD
+                    | #or
+                    \A(?P<month2>\d{1,2}) # MM
+                    [/-]
+                    (?P<day2>\d{1,2}) #DD
+                    [/-]
+                    (?P<year2>\d{4}) #YYYY
+                    """, num, re.VERBOSE)
+    if match:
+        match_dict = match.groupdict()
+        if match_dict.get('month2') != None:
+            match_dict['month'] = match_dict['month2']
+            match_dict['day'] = match_dict['day2']
+            match_dict['year'] = match_dict['year2']
+        del(match_dict['month2'])
+        del(match_dict['day2'])
+        del(match_dict['year2'])
+        match_dict['month'] = int(match_dict['month'])
+        match_dict['day'] = int(match_dict['day'])
+        match_dict['year'] = int(match_dict['year'])
+        return match_dict
+
+#
+# ("9/4/1976", {"month": 9, "day": 4, "year": 1976}),
+#     ("1976-09-04", {"month": 9, "day": 4, "year": 1976}),
+#     ("2015-01-01", {"month": 1, "day": 1, "year": 2015}),
+#     ("02/15/2004", {"month": 2, "day": 15, "year": 2004}),
+#     ("9/4", None),
+#     ("2015", None),
+# ])

textminer/tests/test_separator.py

@@ -4,7 +4,6 @@
 
 import textminer.separator as s
 
-@xfail
 @params("input,expected", [
     ("hello", ['hello']),
     ("hello world", ['hello', 'world']),
@@ -16,7 +15,6 @@ def test_words(input, expected):
     assert s.words(input) == expected
 
 
-@xfail
 @params("input,expected", [
     ("919-555-1212", {"area_code": "919", "number": "555-1212"}),
     ("(919) 555-1212", {"area_code": "919", "number": "555-1212"}),
@@ -57,7 +55,6 @@ def test_money(input, expected):
     assert s.money(input) == expected
 
 
-@xfail
 @params("input,expected", [
     ("63936", {"zip": "63936", "plus4": None}),
     ("50583", {"zip": "50583", "plus4": None}),
@@ -73,7 +70,7 @@ def test_zip(input, expected):
     assert s.zipcode(input) == expected
 
 
-@xfail
+
 @params("input,expected", [
     ("9/4/1976", {"month": 9, "day": 4, "year": 1976}),
     ("1976-09-04", {"month": 9, "day": 4, "year": 1976}),
@@ -82,8 +79,8 @@ def test_zip(input, expected):
     ("9/4", None),
     ("2015", None),
 ])
-def test_date(input, expected):
-    assert s.date(input) == expected
+def test_dates(input, expected):
+    assert s.dates(input) == expected
 
 
 ## HARD MODE BEGINS

textminer/tests/test_validator.py

@@ -4,7 +4,6 @@
 import textminer.validator as v
 
 
-@xfail
 def test_binary_numbers():
     assert v.binary("0")
     assert v.binary("1")
@@ -15,7 +14,6 @@ def test_binary_numbers():
     assert not v.binary("911")
 
 
-@xfail
 def test_binary_even():
     """String must be a binary number and be even."""
 
@@ -24,7 +22,6 @@ def test_binary_even():
     assert not v.binary_even("1011")
 
 
-@xfail
 def test_hexadecimal():
     assert v.hex("CAFE")
     assert v.hex("9F9")
@@ -34,7 +31,6 @@ def test_hexadecimal():
     assert not v.hex("COFFEE")
 
 
-@xfail
 def test_word():
     assert v.word("hello")
     assert v.word("wonderful")
@@ -47,7 +43,6 @@ def test_word():
     assert not v.word("bar*us")
 
 
-@xfail
 def test_words():
     """words can take an optional count argument. In case it exists, the text
     must match that number of words."""
@@ -69,7 +64,6 @@ def test_words():
     assert not v.words("18-wheeler tarbox", count=3)
 
 
-@xfail
 def test_phone_numbers():
     """US phone numbers only."""
 
@@ -84,7 +78,6 @@ def test_phone_numbers():
     assert not v.phone_number("mobile")
 
 
-@xfail
 def test_money():
     """We are just concerned with dollars here."""
 
@@ -110,7 +103,6 @@ def test_money():
     assert not v.money("$$31")
 
 
-@xfail
 def test_zip():
     assert v.zipcode("63936")
     assert v.zipcode("50583")
@@ -125,7 +117,6 @@ def test_zip():
     assert not v.zipcode("8029-3924")
 
 
-@xfail
 def test_date():
     assert v.date("9/4/1976")
     assert v.date("1976-09-04")

textminer/validator.py

@@ -0,0 +1,63 @@
+import re
+
+def binary(num):
+    return re.match(r"[01]+", num)
+
+def binary_even(num):
+    """String must be a binary number and be even."""
+    return re.match(r"[01]+0$", num)
+
+def hex(txt):
+    return re.match(r"\A[0-9A-Fa-f]+\Z", txt)
+    assert v.hex("CAFE")
+    assert v.hex("9F9")
+    assert v.hex("123")
+    assert v.hex("6720EB3A9D1")
+    assert not v.hex("")
+    assert not v.hex("COFFEE")
+
+def word(txt):
+    return re.match(r"\A[\d]*[A-Za-z-]+\Z", txt)
+
+def words(txt, count=0):
+    if count == 0:
+        return re.match(r"\A[\d]*[A-Za-z-\s]+\Z", txt)
+
+    else:
+        txt_list = txt.split()
+        if len(txt_list) != count:
+            return False
+        else:
+            return re.match(r"\A[\d]*[A-Za-z-\s]+\Z", txt)
+
+
+def phone_number(num):
+    """US phone numbers only."""
+    return re.match(r"\(?\d{3}[\.\)]?[.\- ]?\d{3}[.\-]?\d{4}", num)
+
+
+def money(num):
+    """We are just concerned with dollars here."""
+    return re.match(r"""\$  #find dollar sign
+                        ((\d{1,3} # one to three digits
+                        (,\d{3})*) #find comma and 3 digits as many times
+                        | #or
+                        \d+)#zero or more digits
+                        (\.\d{2})?$ #finds a decimal and zero or 1 digits
+                        """, num, re.VERBOSE)
+
+def zipcode(num):
+    return re.match(r"""\d{5} #five digit zipcode
+                    (-\d{4} #can also have dash
+                    | #or
+                    $ #has to end, no more number allowed
+                    )""", num, re.VERBOSE)
+
+
+def date(num):
+    return re.match(r"""\A(\d{1}|\d{2}|\d{4})
+                    [/-]
+                    \d{1,2}
+                    [/-]
+                    (\d{2}|d{4})
+                    """, num, re.VERBOSE)