From: Marcin Koziej <marcin@koziej.info>
Date: Mon, 4 Nov 2013 16:12:54 +0000 (+0100)
Subject: Accept dates in like "2 poł. XIX w."
X-Git-Tag: 1.7~125^2
X-Git-Url: https://git.mdrn.pl/librarian.git/commitdiff_plain/00906f2fc0432cede204c7870e6caecf427d7024?ds=sidebyside

Accept dates in like "2 poł. XIX w."
---

diff --git a/librarian/dcparser.py b/librarian/dcparser.py
index d99aaf0..fff8ac2 100644
--- a/librarian/dcparser.py
+++ b/librarian/dcparser.py
@@ -6,6 +6,8 @@
 from xml.parsers.expat import ExpatError
 from datetime import date
 import time
+import re
+from librarian.util import roman_to_int
 
 from librarian import (ValidationError, NoDublinCore, ParseError, DCNS, RDFNS,
                        WLURI)
@@ -62,10 +64,17 @@ class Person(object):
 
 def as_date(text):
     try:
-        try:
-            t = time.strptime(text, '%Y-%m-%d')
-        except ValueError:
-            t = time.strptime(text, '%Y')
+        # check out the "N. poł X w." syntax
+        m = re.match(u"([12]) *poł[.]? ([MCDXVI]+) .*[.]?", text)
+        if m:
+            half = int(m.groups()[0])
+            century = roman_to_int(str(m.groups()[1]))
+            t = ((century*100 + (half-1)*50), 1, 1)
+        else:
+            try:
+                t = time.strptime(text, '%Y-%m-%d')
+            except ValueError:
+                t = time.strptime(text, '%Y')
         return date(t[0], t[1], t[2])
     except ValueError, e:
         raise ValueError("Unrecognized date format. Try YYYY-MM-DD or YYYY.")
diff --git a/librarian/util.py b/librarian/util.py
new file mode 100644
index 0000000..396c84b
--- /dev/null
+++ b/librarian/util.py
@@ -0,0 +1,117 @@
+# Functions to convert between integers and Roman numerals. Doctest examples included.
+# by Paul Winkler 
+# http://code.activestate.com/recipes/81611-roman-numerals/
+# PSFL (GPL compatible)
+
+def int_to_roman(input):
+    """
+    Convert an integer to Roman numerals.
+
+    Examples:
+    >>> int_to_roman(0)
+    Traceback (most recent call last):
+    ValueError: Argument must be between 1 and 3999
+
+    >>> int_to_roman(-1)
+    Traceback (most recent call last):
+    ValueError: Argument must be between 1 and 3999
+
+    >>> int_to_roman(1.5)
+    Traceback (most recent call last):
+    TypeError: expected integer, got <type 'float'>
+
+    >>> for i in range(1, 21): print int_to_roman(i)
+    ...
+    I
+    II
+    III
+    IV
+    V
+    VI
+    VII
+    VIII
+    IX
+    X
+    XI
+    XII
+    XIII
+    XIV
+    XV
+    XVI
+    XVII
+    XVIII
+    XIX
+    XX
+    >>> print int_to_roman(2000)
+    MM
+    >>> print int_to_roman(1999)
+    MCMXCIX
+    """
+    if type(input) != type(1):
+        raise TypeError, "expected integer, got %s" % type(input)
+    if not 0 < input < 4000:
+        raise ValueError, "Argument must be between 1 and 3999"    
+    ints = (1000, 900,  500, 400, 100,  90, 50,  40, 10,  9,    5,  4,    1)
+    nums = ('M',  'CM', 'D', 'CD','C', 'XC','L','XL','X','IX','V','IV','I')
+    result = ""
+    for i in range(len(ints)):
+        count = int(input / ints[i])
+        result += nums[i] * count
+        input -= ints[i] * count
+    return result
+
+def roman_to_int(input):
+    """
+    Convert a roman numeral to an integer.
+    
+    >>> r = range(1, 4000)
+    >>> nums = [int_to_roman(i) for i in r]
+    >>> ints = [roman_to_int(n) for n in nums]
+    >>> print r == ints
+    1
+
+    >>> roman_to_int('VVVIV')
+    Traceback (most recent call last):
+     ...
+    ValueError: input is not a valid roman numeral: VVVIV
+    >>> roman_to_int(1)
+    Traceback (most recent call last):
+     ...
+    TypeError: expected string, got <type 'int'>
+    >>> roman_to_int('a')
+    Traceback (most recent call last):
+     ...
+    ValueError: input is not a valid roman numeral: A
+    >>> roman_to_int('IL')
+    Traceback (most recent call last):
+     ...
+    ValueError: input is not a valid roman numeral: IL
+    """
+    if type(input) != type(""):
+        raise TypeError, "expected string, got %s" % type(input)
+    input = input.upper()
+    nums = ['M', 'D', 'C', 'L', 'X', 'V', 'I']
+    ints = [1000, 500, 100, 50,  10,  5,    1]
+    places = []
+    for c in input:
+        if not c in nums:
+            raise ValueError, "input is not a valid roman numeral: %s" % input
+    for i in range(len(input)):
+        c = input[i]
+        value = ints[nums.index(c)]
+        # If the next place holds a larger number, this value is negative.
+        try:
+            nextvalue = ints[nums.index(input[i +1])]
+            if nextvalue > value:
+                value *= -1
+        except IndexError:
+            # there is no next place.
+            pass
+        places.append(value)
+    sum = 0
+    for n in places: sum += n
+    # Easiest test for validity...
+    if int_to_roman(sum) == input:
+        return sum
+    else:
+        raise ValueError, 'input is not a valid roman numeral: %s' % input