Merge pull request #5 from minhhaiphys/master

Add kwarg delimiter to TextWriter

README.txt

@@ -14,6 +14,7 @@ record "events" in callback functions
 Refer to the provided command line scripts for ideas on how to use PySTDF:
 
 stdf2text, convert STDF to '|' delimited text format.
+stdf2excel, convert STDF to MS Excel.
 stdf_slice, an example of how to seek to a specific record offset in the STDF.
 
 I have also included a very basic STDF viewer GUI, StdfExplorer.  I have plans 

pystdf/Importer.py

@@ -0,0 +1,86 @@
+#
+# PySTDF - The Pythonic STDF Parser
+# Copyright (C) 2006 Casey Marshall
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+#
+# Modified: 2017 Minh-Hai Nguyen
+#
+
+import numpy as np
+import pandas as pd
+from pystdf.IO import Parser
+from pystdf.Writers import TextWriter
+
+class MemoryWriter:
+    def __init__(self):
+        self.data = []
+    def after_send(self, dataSource, data):
+        self.data.append(data)
+    def write(self,line):
+        self.data.append(line)
+    def flush(self):
+        pass # Do nothing
+
+def ImportSTDF(fname):
+    with open(fname,'rb') as fin:
+        p = Parser(inp=fin)
+        storage = MemoryWriter()
+        p.addSink(storage)
+        p.parse()
+    return storage.data
+
+def STDF2Text(fname,delimiter='|'):
+    """ Convert STDF to a list of text representation
+    """
+    with open(fname,'rb') as fin:
+        p = Parser(inp=fin)
+        storage = MemoryWriter()
+        p.addSink(TextWriter(storage,delimiter=delimiter))
+        p.parse()
+        return storage.data
+    return None
+
+def STDF2Dict(fname):
+    """ Convert STDF to a list of dictionary objects
+    """
+    data = ImportSTDF(fname)
+    data_out = []
+    for datum in data:
+        datum_out = {}
+        RecType = datum[0].__class__.__name__.upper()
+        datum_out['RecType'] = RecType
+        for k,v in zip(datum[0].fieldMap,datum[1]):
+            datum_out[k[0]] = v
+        data_out.append(datum_out)
+    return data_out
+
+def STDF2DataFrame(fname):
+    """ Convert STDF to a dictionary of DataFrame objects
+    """
+    data = ImportSTDF(fname)
+    BigTable = {}
+    for datum in data:
+        RecType = datum[0].__class__.__name__.upper()
+        if RecType not in BigTable.keys():
+            BigTable[RecType] = {}
+        Rec = BigTable[RecType]
+        for k,v in zip(datum[0].fieldMap,datum[1]):
+            if k[0] not in Rec.keys():
+                Rec[k[0]] = []
+            Rec[k[0]].append(v)
+    for k,v in BigTable.items():
+        BigTable[k] = pd.DataFrame(v)
+    return BigTable

pystdf/Writers.py

@@ -31,14 +31,17 @@ def format_by_type(value, field_type):
         return str(value)
 
 class TextWriter:
+    def __init__(self, stream=sys.stdout, delimiter='|'):
+        self.stream = stream
+        self.delimiter = delimiter
 
     @staticmethod
     def text_format(rectype, field_index, value):
         field_type = rectype.fieldStdfTypes[field_index]
         if value is None:
             return ""
         elif rectype is V4.gdr:
-            return '|'.join([str(v) for v in value])
+            return self.delimiter.join([str(v) for v in value])
         elif field_type[0] == 'k': # An Array of some other type
             return ','.join([format_by_type(v, field_type[2:]) for v in value])
         elif rectype is V4.mir or rectype is V4.mrr:
@@ -50,12 +53,9 @@ def text_format(rectype, field_index, value):
         else:
             return str(value)
 
-    def __init__(self, stream=sys.stdout):
-        self.stream = stream
-
     def after_send(self, dataSource, data):
-        line = '%s:%s%s' % (data[0].__class__.__name__.upper(),
-            '|'.join([self.text_format(data[0], i, val) for i, val in enumerate(data[1])]), '\n')
+        line = '%s%s%s\n' % (data[0].__class__.__name__.upper(),self.delimiter,
+            self.delimiter.join([self.text_format(data[0], i, val) for i, val in enumerate(data[1])]))
         self.stream.write(line)
 
     def after_complete(self, dataSource):

scripts/stdf2excel

@@ -0,0 +1,53 @@
+#!/usr/bin/env python
+#
+# PySTDF - The Pythonic STDF Parser
+# Copyright (C) 2006 Casey Marshall
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+#
+# Modified: 2017 Minh-Hai Nguyen
+#
+import sys, os
+from pystdf.Importer import STDF2DataFrame
+import pystdf.V4
+
+
+def toExcel(fname,tables):
+    """ Export the tables from toTables to Excel
+    """
+    writer = pd.ExcelWriter(fname)
+    for k,v in tables.items():
+        # Make sure the order of columns complies the specs
+        record = [r for r in V4.records if r.__class__.__name__.upper()==k]
+        if len(record)==0:
+            print("Ignore exporting table %s: No such record type exists." %k)
+        else:
+            columns = [field[0] for field in record[0].fieldMap]
+            v.to_excel(writer,sheet_name=k,columns=columns,index=False,na_rep="N/A")
+    writer.save()
+
+if __name__=="__main__":
+    if len(sys.argv)==1:
+        print("Usage: %s <stdf file>" % (sys.argv[0]))
+    else:
+        fin = sys.argv[1]
+        if len(sys.argv)>2:
+            fout = sys.argv[2]
+        else:
+            fout = fin[:fin.rfind('.')]+".xlsx"
+        print("Importing %s" %fin)
+        dfs= STDF2DataFrame(fin)
+        print("Exporting to %s" %fout)
+        toExcel(fout,dfs)