summaryrefslogtreecommitdiff
path: root/trunk/src/examples/parseTabularData.py
diff options
context:
space:
mode:
authorptmcg <ptmcg@9bf210a0-9d2d-494c-87cf-cfb32e7dff7b>2016-08-09 00:23:49 +0000
committerptmcg <ptmcg@9bf210a0-9d2d-494c-87cf-cfb32e7dff7b>2016-08-09 00:23:49 +0000
commitb2c3ade75384efe76b8774b607e17fe98fab92ef (patch)
treeb162262f3f0a4bc976d45bed08ccfc6cc9a2eb23 /trunk/src/examples/parseTabularData.py
parent0be19d2d8545f1ac4b93ffd0d10524613837ba39 (diff)
downloadpyparsing-b2c3ade75384efe76b8774b607e17fe98fab92ef.tar.gz
TagTag for 2.1.6 release
git-svn-id: svn://svn.code.sf.net/p/pyparsing/code/tags/pyparsing_2.1.6@402 9bf210a0-9d2d-494c-87cf-cfb32e7dff7b
Diffstat (limited to 'trunk/src/examples/parseTabularData.py')
-rw-r--r--trunk/src/examples/parseTabularData.py50
1 files changed, 50 insertions, 0 deletions
diff --git a/trunk/src/examples/parseTabularData.py b/trunk/src/examples/parseTabularData.py
new file mode 100644
index 0000000..3846310
--- /dev/null
+++ b/trunk/src/examples/parseTabularData.py
@@ -0,0 +1,50 @@
+#
+# parseTabularData.py
+#
+# Example of parsing data that is formatted in a tabular listing, with
+# potential for missing values. Uses new addCondition method on
+# ParserElements.
+#
+# Copyright 2015, Paul McGuire
+#
+from pyparsing import col,Word,Optional,alphas,nums,ParseException
+
+table = """\
+ 1 2
+12345678901234567890
+COLOR S M L
+RED 10 2 2
+BLUE 5 10
+GREEN 3 5
+PURPLE 8"""
+
+# function to create column-specific parse conditions
+def mustMatchCols(startloc,endloc):
+ return lambda s,l,t: startloc <= col(l,s) <= endloc
+
+# helper to define values in a space-delimited table
+# (change empty_cell_is_zero to True if a value of 0 is desired for empty cells)
+def tableValue(expr, colstart, colend):
+ empty_cell_is_zero = False
+ if empty_cell_is_zero:
+ return Optional(expr.copy().addCondition(mustMatchCols(colstart,colend),
+ message="text not in expected columns"),
+ default=0)
+ else:
+ return Optional(expr.copy().addCondition(mustMatchCols(colstart,colend),
+ message="text not in expected columns"))
+
+
+# define the grammar for this simple table
+colorname = Word(alphas)
+integer = Word(nums).setParseAction(lambda t: int(t[0])).setName("integer")
+row = (colorname("name") +
+ tableValue(integer, 11, 12)("S") +
+ tableValue(integer, 15, 16)("M") +
+ tableValue(integer, 19, 20)("L"))
+
+# parse the sample text - skip over the header and counter lines
+for line in table.splitlines()[3:]:
+ print(line)
+ print(row.parseString(line).dump())
+ print('')