From 453ef7eb2716ac2faef51dfca931e7f76bef6cd5 Mon Sep 17 00:00:00 2001 From: Kacper Dudzic Date: Fri, 22 Apr 2022 22:25:21 +0200 Subject: [PATCH] jurisdiction regex --- dev-0/out.tsv | 83 ++++++++++++++++++++ run.py | 33 ++++++++ test-A/out.tsv | 203 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 319 insertions(+) create mode 100644 dev-0/out.tsv create mode 100644 run.py create mode 100644 test-A/out.tsv diff --git a/dev-0/out.tsv b/dev-0/out.tsv new file mode 100644 index 0000000..8b409bb --- /dev/null +++ b/dev-0/out.tsv @@ -0,0 +1,83 @@ +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=Delaware +jurisdiction=New_Jersey +jurisdiction=New_York + +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=Massachusetts +jurisdiction=Minnesota +jurisdiction=California +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=Iowa +jurisdiction=California +jurisdiction=Virginia +jurisdiction=North_Carolina +jurisdiction=Arizona +jurisdiction=Indiana +jurisdiction=New_Jersey +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Georgia +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=California +jurisdiction=Minnesota +jurisdiction=California +jurisdiction=Kentucky +jurisdiction=Minnesota +jurisdiction=Ohio +jurisdiction=Massachusetts +jurisdiction=California +jurisdiction=Minnesota +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Illinois +jurisdiction=Minnesota +jurisdiction=Texas +jurisdiction=New_Jersey +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=Georgia +jurisdiction=Delaware +jurisdiction=Oregon +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Massachusetts +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Illinois +jurisdiction=Idaho +jurisdiction=Washington +jurisdiction=California +jurisdiction=New_York +jurisdiction=California +jurisdiction=Utah +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=Virginia +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=Illinois +jurisdiction=California +jurisdiction=Delaware + +jurisdiction=Texas +jurisdiction=California +jurisdiction=Washington +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=New_York +jurisdiction=Washington +jurisdiction=Illinois diff --git a/run.py b/run.py new file mode 100644 index 0000000..cc5c6a0 --- /dev/null +++ b/run.py @@ -0,0 +1,33 @@ +import re +import sys + +filename = sys.argv[1] + +with open(filename, encoding='utf-8') as f_in, open('out.tsv', 'w', encoding='utf-8') as f_out: + for line in f_in: + cols = line.split('\t') + clean_col = re.sub(r'(\\n)|(\\f)|(\\t)|(\\)', ' ', cols[-1]) + clean_col = re.sub('[^A-Za-z ]', ' ', clean_col) + clean_col = re.sub(' +', ' ', clean_col) + stateof2words = re.search('[sS]tate of [A-Z]\w+( \w+)?', clean_col) + if stateof2words: + stateof2words = stateof2words.group().split() + if stateof2words[2] in ['New', 'South', 'West', 'Rhode', 'North']: + f_out.write('jurisdiction=' + stateof2words[2] + '_' + stateof2words[3] + '\n') + else: + f_out.write('jurisdiction=' + stateof2words[2] + '\n') + else: + found = False + for word in ['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California', 'Colorado', 'Connecticut', 'Delaware', + 'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana', 'Iowa', 'Kansas', 'Kentucky', + 'Louisiana', 'Maine', 'Maryland', 'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi', + 'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire', 'New Jersey', 'New Mexico', + 'New York', 'North Carolina', 'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania', + 'Rhode Island', 'South Carolina', 'South Dakota', 'Tennessee', 'Texas', 'Utah', 'Vermont', + 'Virginia', 'Washington', 'West Virginia', 'Wisconsin', 'Wyoming']: + if word in clean_col: + f_out.write('jurisdiction=' + word + '\n') + found = True + break + if not found: + f_out.write('\n') diff --git a/test-A/out.tsv b/test-A/out.tsv new file mode 100644 index 0000000..ae7f440 --- /dev/null +++ b/test-A/out.tsv @@ -0,0 +1,203 @@ +jurisdiction=Ohio +jurisdiction=Delaware +jurisdiction=Louisiana +jurisdiction=New_York +jurisdiction=Nevada +jurisdiction=Colorado +jurisdiction=Colorado +jurisdiction=California +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=California +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=California +jurisdiction=Washington +jurisdiction=Victoria +jurisdiction=Florida +jurisdiction=Delaware +jurisdiction=Florida +jurisdiction=New_York +jurisdiction=California +jurisdiction=Florida +jurisdiction=New_York +jurisdiction=Washington +jurisdiction=Texas +jurisdiction=Delaware +jurisdiction=Georgia +jurisdiction=Washington +jurisdiction=Delaware +jurisdiction=Nevada +jurisdiction=California +jurisdiction=California +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=New York +jurisdiction=Delaware +jurisdiction=Florida +jurisdiction=California +jurisdiction=Virginia +jurisdiction=Pennsylvania +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=California +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=New_Jersey +jurisdiction=California +jurisdiction=Texas +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=Pennsylvania +jurisdiction=California +jurisdiction=Georgia +jurisdiction=Delaware +jurisdiction=Delaware +jurisdiction=Massachusetts +jurisdiction=Connecticut +jurisdiction=California +jurisdiction=Texas +jurisdiction=Delaware +jurisdiction=Virginia +jurisdiction=Delaware +jurisdiction=Washington +jurisdiction=Minnesota +jurisdiction=Oregon +jurisdiction=Texas +jurisdiction=Colorado +jurisdiction=Colorado +jurisdiction=Nevada +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=Illinois +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=Florida +jurisdiction=Virginia +jurisdiction=New_York +jurisdiction=Nevada +jurisdiction=Delaware +jurisdiction=New_Jersey +jurisdiction=North_Carolina +jurisdiction=Minnesota +jurisdiction=Connecticut +jurisdiction=North_Carolina +jurisdiction=Kansas +jurisdiction=Florida +jurisdiction=Washington +jurisdiction=Oregon +jurisdiction=New_York +jurisdiction=Georgia +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=Colorado +jurisdiction=California +jurisdiction=Tennessee +jurisdiction=Ohio +jurisdiction=Minnesota +jurisdiction=Delaware +jurisdiction=California +jurisdiction=Connecticut +jurisdiction=Maryland +jurisdiction=Delaware +jurisdiction=Utah +jurisdiction=California +jurisdiction=Utah +jurisdiction=Colorado +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=California +jurisdiction=New_York +jurisdiction=Virginia +jurisdiction=Delaware +jurisdiction=Texas +jurisdiction=Massachusetts +jurisdiction=Colorado +jurisdiction=New_York +jurisdiction=Michigan +jurisdiction=Pennsylvania +jurisdiction=Japan +jurisdiction=New_Jersey +jurisdiction=New_York +jurisdiction=Minnesota +jurisdiction=Ohio +jurisdiction=Oregon +jurisdiction=New_Jersey +jurisdiction=Florida +jurisdiction=Oregon +jurisdiction=Massachusetts +jurisdiction=Ohio +jurisdiction=Minnesota +jurisdiction=Maryland +jurisdiction=Indiana +jurisdiction=California +jurisdiction=Virginia +jurisdiction=Tennessee +jurisdiction=Delaware +jurisdiction=Maryland +jurisdiction=Pennsylvania +jurisdiction=Ohio +jurisdiction=California +jurisdiction=New_Jersey +jurisdiction=Colorado +jurisdiction=Indiana +jurisdiction=Virginia +jurisdiction=Minnesota +jurisdiction=New York +jurisdiction=Delaware +jurisdiction=New_York +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Louisiana +jurisdiction=Georgia +jurisdiction=New_York +jurisdiction=New_York +jurisdiction=Oregon +jurisdiction=Nevada +jurisdiction=California +jurisdiction=North_Carolina +jurisdiction=California +jurisdiction=Georgia +jurisdiction=California +jurisdiction=New_York + +jurisdiction=New_York +jurisdiction=Indiana +jurisdiction=Georgia +jurisdiction=New_Jersey +jurisdiction=Minnesota +jurisdiction=North_Carolina +jurisdiction=Georgia +jurisdiction=Kentucky +jurisdiction=Nevada +jurisdiction=Missouri +jurisdiction=Colorado +jurisdiction=Connecticut +jurisdiction=Delaware +jurisdiction=North_Carolina +jurisdiction=California +jurisdiction=Georgia +jurisdiction=California +jurisdiction=New_York +jurisdiction=Pennsylvania +jurisdiction=California +jurisdiction=Maryland +jurisdiction=California +jurisdiction=Delaware +jurisdiction=Pennsylvania +jurisdiction=New_York +jurisdiction=Delaware +jurisdiction=Virginia +jurisdiction=Delaware +jurisdiction=Nevada +jurisdiction=Nevada +jurisdiction=Delaware +jurisdiction=California +jurisdiction=Colorado +