Changed xml2csv's --header option to --noheader

Author: knadh

README.md

@@ -1,8 +1,8 @@
 # xmlutils.py
-xmlutils.py is a set of Python utilities for processing xml files serially, 
-namely converting them to other formats (SQL, CSV, JSON). The scripts use 
-ElementTree.iterparse() to iterate through nodes in an XML file, thus not 
-needing to load the whole DOM into memory. The scripts can be used to churn 
+xmlutils.py is a set of Python utilities for processing xml files serially  
+for converting them to various formats (SQL, CSV, JSON). The scripts use 
+ElementTree.iterparse() to iterate through nodes in an XML document, thus not 
+needing to load the entire DOM into memory. The scripts can be used to churn 
 through large XML files (albeit taking long :P) without memory hiccups.
 
 Blind conversion of XML to CSV and SQL is not recommended.
@@ -43,11 +43,11 @@ xml2csv --input "samples/fruits.xml" --output "samples/fruits.csv" --tag "item"
 --output 	Output CSV file's filename*
 --tag 		The tag of the node that represents a single record (Eg: item, record)*
 --delimiter 	Delimiter for seperating items in a row. Default is , (a comma followed by a space)
---ignore 	A space separated list of element tags in the XML document to ignore.
---header 	Whether to print the CSV header (list of fields) in the first line; 1=yes, 0=no. Default is 1.
+--ignore 	A space separated list of element tags in the XML document to ignore
+--noheader 	Exclude CSV fields header (first line). Off by default
 --encoding 	Character encoding of the document. Default is utf-8
 --limit 	Limit the number of records to be processed from the document to a particular number. Default is no limit (-1)
---buffer 	The number of records to be kept in memory before it is written to the output CSV file. Helps reduce the number of disk writes. Default is 1000. 
+--buffer 	The number of records to be kept in memory before it is written to the output CSV file. Helps reduce the number of disk writes. Default is 1000
 ```
 
 ##xml2sql

samples/fruits.csv

@@ -1,4 +1,3 @@
-id,name,price,quantity
 "1000","Apple","4","133"
 "1001","Apricot","5","175"
 "1002","Avocado","5","182"

setup.py

@@ -4,7 +4,7 @@
 
 setup(
 	name="xmlutils",
-	version="0.94",
+	version="1.0",
 	description="A set of utilities for processing XML documents and converting to other formats",
 	author="Kailash Nadh",
 	author_email="kailash.nadh@gmail.com",

xmlutils/console.py

@@ -50,9 +50,9 @@ def run_xml2csv():
 	parser.add_argument('--input', dest='input_file', required=True, help='input xml filename')
 	parser.add_argument('--output', dest='output_file', required=True, help='output csv filename')
 	parser.add_argument('--tag', dest='tag', required=True, help='the record tag. eg: item')
-	parser.add_argument('--delimiter', dest='delimiter', default=',', help='delimiter character. (default=, comma-space)')
+	parser.add_argument('--delimiter', dest='delimiter', default=',', help='delimiter character. (default=,)')
 	parser.add_argument('--ignore', dest='ignore', default='', nargs='+', help='list of tags to ignore')
-	parser.add_argument('--header', dest='header', action='store_false', default=True, help='print csv header (default=True)')
+	parser.add_argument('--noheader', dest='noheader', action='store_true', help='exclude csv header (default=False)')
 	parser.add_argument('--encoding', dest='encoding', default='utf-8', help='character encoding (default=utf-8)')
 	parser.add_argument('--limit', type=int, dest='limit', default=-1, help='maximum number of records to process')
 	parser.add_argument('--buffer_size', type=int, dest='buffer_size', default='1000',
@@ -62,7 +62,7 @@ def run_xml2csv():
 
 	converter = xml2csv(args.input_file, args.output_file, args.encoding)
 	num = converter.convert(tag=args.tag, delimiter=args.delimiter, ignore=args.ignore,
-							header=args.header, limit=args.limit, buffer_size=args.buffer_size)
+							noheader=args.noheader, limit=args.limit, buffer_size=args.buffer_size)
 
 	print "\n\nWrote", num, "records to", args.output_file
 

xmlutils/xml2csv.py

@@ -36,7 +36,7 @@ def __init__(self, input_file, output_file, encoding='utf-8'):
 			raise
 
 
-	def convert(self, tag="item", delimiter=",", ignore=[], header=True,
+	def convert(self, tag="item", delimiter=",", ignore=[], noheader=False,
 				limit=-1, buffer_size=1000):
 
 		"""Convert the XML file to SQL file
@@ -69,7 +69,7 @@ def convert(self, tag="item", delimiter=",", ignore=[], header=True,
 			# if elem is an unignored child node of the record tag, it should be written to buffer
 			should_write = elem.tag != tag and started and elem.tag not in ignore
 			# and if a header is required and if there isn't one
-			should_tag = not tagged and should_write and header
+			should_tag = not tagged and should_write and not noheader
 
 			if event == 'start':
 				if elem.tag == tag and not started: