From 14419f066973d26192bea9b97707bd872af772c7 Mon Sep 17 00:00:00 2001
From: Paul Duncan <pabs@pablotron.org>
Date: Thu, 2 Mar 2023 17:09:02 -0500
Subject: initial commit

---
 section-parse-insane.py | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 section-parse-insane.py

(limited to 'section-parse-insane.py')

diff --git a/section-parse-insane.py b/section-parse-insane.py
new file mode 100644
index 0000000..e7c6d9e
--- /dev/null
+++ b/section-parse-insane.py
@@ -0,0 +1,40 @@
+#!/usr/bin/python3
+
+#
+# section-parse-insane.py: scan standard input and do the following:
+#
+# 1. look for a section that begins with "test-text "STUFF/foo" and ends
+#    with a blank line.
+# 2. print the "bar.DIGITS" suffix for each line in the section
+#
+# Example:
+#   > cat input.txt
+#   test-text "blah blah blah garbage/foo"
+#   random crap bar.1
+#   random crap bar.2
+#   random crap bar.3
+#   random crap bar.4
+#   
+#   test-text "blah blah blah garbage/apple"
+#   random crap bar.1
+#   random crap bar.2
+#   random crap bar.3
+#   random crap bar.4
+#   > ./section-parse-insane.py < input.txt
+#   bar.1
+#   bar.2
+#   bar.3
+#   bar.4
+#
+
+# load libraries
+import re
+import sys
+
+# section and row matches
+S = re.compile('(?m)^test-text "[^"]+/foo"\n((?:^[^\n]*bar\.\d+\n)+)^\s*\n')
+B = re.compile('^.*(bar\.\d+)$')
+
+# read stdin, extract section body, split by line, map rows to suffix,
+# and print to stdout
+print("\n".join([B.sub('\\1', s) for s in S.search(sys.stdin.read())[1].strip().split("\n")]))
-- 
cgit v1.2.3