| Server IP : 88.222.222.18 / Your IP : 216.73.216.254 Web Server : LiteSpeed System : Linux id-dci-web1986.main-hosting.eu 5.14.0-611.26.1.el9_7.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Jan 29 05:24:47 EST 2026 x86_64 User : u686484674 ( 686484674) PHP Version : 8.0.30 Disable Function : system, exec, shell_exec, passthru, mysql_list_dbs, ini_alter, dl, symlink, link, chgrp, leak, popen, apache_child_terminate, virtual, mb_send_mail MySQL : OFF | cURL : ON | WGET : ON | Perl : OFF | Python : OFF | Sudo : OFF | Pkexec : OFF Directory : /opt/gsutil/third_party/pyparsing/examples/ |
Upload File : |
# removeLineBreaks.py
#
# Demonstration of the pyparsing module, converting text files
# with hard line-breaks to text files with line breaks only
# between paragraphs. (Helps when converting downloads from Project
# Gutenberg - https://www.gutenberg.org/ - to import to word processing apps
# that can reformat paragraphs once hard line-breaks are removed.)
#
# Uses parse actions and transformString to remove unwanted line breaks,
# and to double up line breaks between paragraphs.
#
# Copyright 2006, by Paul McGuire
#
import pyparsing as pp
line_end = pp.LineEnd()
# define an expression for the body of a line of text - use a predicate condition to
# accept only lines with some content.
def mustBeNonBlank(t):
return t[0] != ""
# could also be written as
# return bool(t[0])
lineBody = pp.SkipTo(line_end).addCondition(
mustBeNonBlank, message="line body can't be empty"
)
# now define a line with a trailing lineEnd, to be replaced with a space character
textLine = lineBody + line_end().setParseAction(pp.replaceWith(" "))
# define a paragraph, with a separating lineEnd, to be replaced with a double newline
para = pp.OneOrMore(textLine) + line_end().setParseAction(pp.replaceWith("\n\n"))
# run a test
test = """
Now is the
time for
all
good men
to come to
the aid of their
country.
"""
print(para.transformString(test))
# process an entire file
# Project Gutenberg EBook of Successful Methods of Public Speaking, by Grenville Kleiser
# Download from http://www.gutenberg.org/cache/epub/18095/pg18095.txt
#
with open("18095-8.txt") as source_file:
original = source_file.read()
# use transformString to convert line breaks
transformed = para.transformString(original)
with open("18095-8_reformatted.txt", "w") as transformed_file:
transformed_file.write(transformed)