case_scraper 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a5a0a100c1d0871d4ef3e2e2681e8646aa4a73b8
-  data.tar.gz: 7c5fdfcd9622f9654926f4c63ea1db833e9765ee
+  metadata.gz: 9326a2861a86a4f00775fe88c5017036847c688f
+  data.tar.gz: 37918563e595a7bc4022af73214b826f354b0d50
 SHA512:
-  metadata.gz: f3c9f4d916cdfad161f1c0a0128040cd5005a589aa7266d202ffe10928d6dc98933c7992a73395d6a45bbd40e70936c3a6dc88bc193f289c945a6d46331337db
-  data.tar.gz: aa4a61b9e6fd18370f3f42396fb3ce65a9a09284a01cf28ca03c9be99a730a5a23308e56544fd7cc6df7ad6a8a2ec1a2667c2b7b4522437ec367d7965159948c
+  metadata.gz: 3590bc69958a214affe3a1760215c73d8d45fa9ae41e4119a982a6512bac1df1b182631736025036c1b7b7ef1025bac9f172cd88f0690f1db2decb87d1bd1171
+  data.tar.gz: a65d66e841a8d06083864591c4c81989a2e87e8ba5b394e08bd8510b8e3579807cc443654fa563b2ec6b546f7d68b52dab32a17c8052099518f5727ab80675e6

data/lib/case_scraper.rb

@@ -1,12 +1,33 @@
 # case_scraper
 #
-# This script uses the Yomu library to extract the text from a legal brief in RTF format. It then uses regular expressions to search the document for case citations and extract the volume, reporter, and starting page for each case. The case citations are then output to a text file, with one citation per line.
+# This script uses the Yomu library 
+# to extract the text from a legal
+# brief in RTF format. It then uses
+# regular expressions to search the
+# document for case citations and
+# extract the volume, reporter, and
+# starting page for each case. The case
+# citations are then output to a text
+# file, with one citation per line.
 #
-# This is an experimental script. Use at your own risk and please be sure to check the output against the list of cases in the original brief to ensure you have a complete list.
+# This is an experimental script. Use 
+# at your own risk and please be sure 
+# to check the output against the 
+# list of cases in the original brief 
+# to ensure you have a complete list.
 #
-# THIS SCRIPT ONLY FOCUSES ON REPORTED U.S. STATE AND FEDERAL CASELAW AND UNREPORTED U.S. STATE AND FEDERAL CASELAW FOR WHICH A LEXIS OR WESTLAW CITATION IS AVAILABLE. IT IS NOT DESIGNED TO DETECT CITATIONS TO CASELAW FROM ANY OTHER JURISDICTION.
+# THIS SCRIPT ONLY FOCUSES ON 
+# REPORTED U.S. STATE AND FEDERAL 
+# CASELAW AND UNREPORTED U.S. STATE 
+# AND FEDERAL CASELAW FOR WHICH A 
+# LEXIS OR WESTLAW CITATION IS 
+# AVAILABLE. IT IS NOT DESIGNED TO 
+# DETECT CITATIONS TO CASELAW FROM 
+# ANY OTHER JURISDICTION.
 #
-# THIS SCRIPT ONLY EXTRACTS CASE CITATIONS, NOT CITATIONS FOR STATUTES OR OTHER AUTHORITIES.
+# THIS SCRIPT ONLY EXTRACTS CASE 
+# CITATIONS, NOT CITATIONS FOR 
+# STATUTES OR OTHER AUTHORITIES.
 #
 # Author: Greg Kochansky
 # E-mail: greg@greg-k.com
@@ -17,7 +38,8 @@
 
 require 'yomu'
 
-# Test that input and output files are specified.
+# Test that input and output files 
+# are specified.
 
 unless ARGV.length == 2
   puts "You must include an input filename (RTF format) and an output filename (TXT format)."
@@ -25,24 +47,27 @@ unless ARGV.length == 2
   exit
 end
 
-# Set the two command line arguments as variables.
+# Set the two command line arguments 
+# as variables.
 
 input = ARGV[0]
 output = ARGV[1]
 
-# Import body text from the input RTF file.
+# Import body text from the input RTF 
+# file.
 
 data = File.read input
 text = Yomu.read :text, data
 
-# Test whether output file already exists.
+# Test whether output file already 
+# exists.
 #
 # If so, then warn before overwriting.
 #
 # If not, then create the output file.
 
 if File.exist?(output)
-  puts "WARNING: if #{input} already exists, then it will be overwritten."
+  puts "WARNING: #{input} already exists. It will be overwritten."
   puts "Press CTRL-C to cancel, or press RETURN to proceed."
   print "[CRTL-C or RETURN?]"
   STDIN.gets
@@ -56,9 +81,20 @@ else
   target = File.open(output, 'w')
 end
   
-# Using regular expressions, extract the case volume, the reporter abbreviation, and the starting page number for (hopefully . . . ) each full case citation in the brief.
+# Using regular expressions, extract 
+# the case volume, the reporter 
+# abbreviation, and the starting page 
+# number for (hopefully . . . ) each 
+# full case citation in the brief.
 #
-# The regular expressions should catch common variations, including spacing or lack of spacing in the reporter abbreviation, state-specific citation formats for New York and California, and Westlaw and LEXIS citations for unpublished rulings.
+# The regular expressions should
+# catch common variations, including 
+# spacing or lack of spacing in the 
+# reporter abbreviation, 
+# state-specific citation formats for 
+# New York and California, and
+# Westlaw and LEXIS citations for 
+# unpublished rulings.
 
 puts "Scraping case citations from #{input}."
 text.scan(/\d+\s\i*\w+\.+\s*\w*\.*\s*\w*\.*\s*\w*\.*\s\d+/) { |w| target.write "#{w}\n" }
@@ -69,9 +105,15 @@ puts "Writing case citations to #{output}."
 
 target.close()
 
-# Open the output file in the user's default text editor.
+# Open the output file in the user's 
+# default text editor.
 #
-# The citation list, one per line, is in the appropriate format for cutting and pasting directly into Westlaw "Find & Print." (The maximum number of lines for a single query is 99.)
+# The citation list, one per line, is 
+# in the appropriate format for 
+# cutting and pasting directly into 
+# Westlaw "Find & Print." (The 
+# maximum number of lines for a 
+# single query is 99.)
 
 %x{ call #{output} }
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: case_scraper
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Greg Kochansky