[REF] refactor code, now the row is a simple object that can be accessible with a dict (this is needed for the next step "merging 05 row in 04" fix regex missing \n at the end of line, add type G_ALL as label can have a various character

Author: sebastienbeau

cfonb/parser/__init__.py

@@ -1,3 +1,3 @@
 # cfonb shortcuts
 from cfonb.parser.common import Row, ParsingError,\
-        G__, G_N, G_N_, G_A, G_A_, G_AN, G_AN_, G_AMT
+        G__, G_N, G_N_, G_A, G_A_, G_AN, G_AN_, G_AMT, G_ALL

cfonb/parser/common.py

@@ -19,6 +19,9 @@
 # cfonb amount rule
 G_AMT = r'(\d{13}[{}A-R]{1})'
 
+# all
+G_ALL = r'(.{%d})'
+
 
 class ParsingError(Exception):
     """Simple parsing Exception for the module.
@@ -45,54 +48,26 @@ class Row(object):
     """Generic row object to manage bank file parsing, compare and reading.
     """
 
-    def __init__(self):
-        """Empty all at start.
-        """
-        self.empty()
-
-    def empty(self):
-        """Initializes values to their default values.
-        """
-        self.line_nb = None
-        self.__list  = dict()
-        self.__dict  = dict()
-        self.__obj   = None
-        self.__db_id = None
-
-    def parse(self, re, keys, line, line_nb=None):
+    def __init__(self, re, keys, line):
         """Parses flat line according re rules, line and additional info.
 
         :param re: regular expression to match with
         :param keys: keys values to build dict and object variables for the row
         :param line: the flat line to be parsed
-        :param line_nb: optional info to keep index in the original file
         """
         # do re match
         match = re.match(line)
         # re check
         if match is None:
-            self.empty()
             raise ParsingError('line is invalid: "%s"' % line)
         else:
-            self.line_nb = line_nb
-            self.__list = list(match.groups())
-            self.__dict = dict(zip(keys, self.__list))
-            self.__obj = Obj(**self.__dict)
-
-    def as_list(self):
-        return self.__list
-
-    def as_dict(self):
-        return self.__dict
-
-    def as_obj(self):
-        return self.__obj
+            self.__dict__ = dict(zip(keys, list(match.groups())))
 
-    def __str__(self) :
-        return str(self.__dict)
+    def __getitem__(self, attr):
+        return getattr(self, attr)
 
-    def __eq__(self, other) :
-        return self.__dict == other.__dict
+    def __setitem__(self, attr, value):
+        return setattr(self, attr, value) 
 
 
 def parse_amount(amount_str, nb_of_dec):

cfonb/parser/statement.py

@@ -6,7 +6,7 @@
 
 
 HEAD_RE = re.compile(
-        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s$'
+        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s\n$'
         % {
             'a': '(01)',               # record code
             'b': parser.G_N   % 5,     # bank code
@@ -59,17 +59,8 @@
     ]
 
 
-def parse_head(line):
-    # init row
-    row = parser.Row()
-    # set row data
-    row.parse(HEAD_RE, HEAD_KEYS, line)
-    # return initialized row
-    return row
-
-
 CONTENT_4_RE = re.compile(
-        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s%(n)s%(o)s%(p)s%(q)s%(r)s%(s)s$'
+        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s%(n)s%(o)s%(p)s%(q)s%(r)s%(s)s\n$'
         % {
             'a': '(04)',               # record code
             'b': parser.G_N   % 5,     # bank code
@@ -83,9 +74,10 @@ def parse_head(line):
             'j': parser.G_N   % 6,     # operation date
             'k': parser.G_N_  % 2,     # reject code
             'l': parser.G_N   % 6,     # value date
-            'm': parser.G_AN_ % 31,    # label
+            'm': parser.G_ALL % 31,    # label
             'n': parser.G_AN_ % 2,     # _
-            'o': parser.G_N   % 7,     # reference
+            'o': parser.G_AN   % 7,    # reference in CFONB norme it's G_N
+                                       # but in the real world it's an G_AN 
             'p': parser.G_AN_ % 1,     # exempt code
             'q': parser.G_AN_ % 1,     # _
             'r': parser.G_AMT,         # amount
@@ -140,31 +132,23 @@ def parse_head(line):
     ]
 
 
-def parse_content_4(line):
-    # init row
-    row = parser.Row()
-    # set row data
-    row.parse(CONTENT_4_RE, CONTENT_4_KEYS, line)
-    # return initialized row
-    return row
-
 
 CONTENT_5_RE = re.compile(
-        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s%(n)s$'
+        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s%(n)s\n$'
         % {
             'a': '(05)',               # record code
             'b': parser.G_N   % 5,     # bank code
             'c': parser.G_AN  % 4,     # internal code
             'd': parser.G_N   % 5,     # desk code
             'e': parser.G_A_  % 3,     # currency code
             'f': parser.G_N_  % 1,     # nb of decimal
-            'g': parser.G__   % 1,     # _
+            'g': parser.G_AN_ % 1,     # _
             'h': parser.G_AN  % 11,    # account nb
             'i': parser.G_AN  % 2,     # operation code
             'j': parser.G_N   % 6,     # operation date
             'k': parser.G__   % 5,     # _
             'l': parser.G_AN  % 3,     # qualifier
-            'm': parser.G_AN  % 70,    # additional info
+            'm': parser.G_ALL % 70,    # additional info
             'n': parser.G__   % 2,     # _
             }
         )
@@ -206,20 +190,10 @@ def parse_content_4(line):
     ]
 
 
-def parse_content_5(line):
-    """NOT TESTED
-    """
-    # init row
-    row = parser.Row()
-    # set row data
-    row.parse(CONTENT_5_RE, CONTENT_5_KEYS, line)
-    # return initialized row
-    return row
-
 
 
 FOOT_RE = re.compile(
-        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s$'
+        r'^%(a)s%(b)s%(c)s%(d)s%(e)s%(f)s%(g)s%(h)s%(i)s%(j)s%(k)s%(l)s%(m)s\n$'
         % {
             'a': '(07)',               # record code
             'b': parser.G_N   % 5,     # bank code
@@ -272,14 +246,6 @@ def parse_content_5(line):
     ]
 
 
-def parse_footer(line):
-    # init row
-    row = parser.Row()
-    # set row data
-    row.parse(FOOT_RE, FOOT_KEYS, line)
-    # return initialized row
-    return row
-
 
 class Statement(object):
     """Satement file parser and container. Parse file object to corresponding
@@ -292,25 +258,44 @@ def __init__(self):
         self.footer   = None
         self.lines  = list()
 
+    def parse_header(self, line):
+        self.header = parser.Row(HEAD_RE, HEAD_KEYS, line)
+
+    def parse_footer(self, line):
+        self.footer = parser.Row(FOOT_RE, FOOT_KEYS, line)
+
+    def parse_content_4(self, line):
+        # init row
+        row = parser.Row(CONTENT_4_RE, CONTENT_4_KEYS, line)
+        # return initialized row
+        return row
+
+    def parse_content_5(self, line):
+        """NOT TESTED
+        """
+        # init row
+        row = parser.Row(CONTENT_5_RE, CONTENT_5_KEYS, line)
+        # return initialized row
+        return row
+
+
     def parse(self, file_obj):
         file_lines  = file_obj.readlines()
         # header and footer
-        self.header = parser.Row()
-        self.header.parse(HEAD_RE, HEAD_KEYS, file_lines[0])
-        self.footer   = parser.Row()
-        self.footer.parse(FOOT_RE, FOOT_KEYS, file_lines[-1])
+        self.parse_header(file_lines.pop(0))
+        self.parse_footer(file_lines.pop())
+
         # content
-        for i, l in enumerate(file_lines[1:-1]):
+        for index, line in enumerate(file_lines):
             # parse line
-            row = parser.Row()
-            if CONTENT_4_RE.match(l):
-                row.parse(CONTENT_4_RE, CONTENT_4_KEYS, l, line_nb=i)
-            elif CONTENT_5_RE.match(l):
-                row.parse(CONTENT_5_RE, CONTENT_5_KEYS, l, line_nb=i)
+            if CONTENT_4_RE.match(line):
+                row = self.parse_content_4(line)
+            elif CONTENT_5_RE.match(line):
+                row = self.parse_content_5(line)
             else:
-                raise parser.ParsingError('line %s is invalid: "%s"' % (i, l))
+                if line[0:2] in ['01', '07']:#we don't take care of subtotal
+                    continue
+                else:
+                    raise parser.ParsingError('line %s is invalid: "%s"' % (index, line))
             # update content
             self.lines.append(row)
-
-
-