Skip to content
This repository was archived by the owner on Nov 16, 2023. It is now read-only.

Renamed URL scripts and reflected this change inside these files #348

Merged
mstfbl merged 6 commits into from
Oct 24, 2019
Merged

Renamed URL scripts and reflected this change inside these files #348

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d0afd1b
Renamed URL scripts and reflected this change inside these files
mstfbl Oct 24, 2019
3a406ef
Fix small type in change_http_urls_to_https.py
mstfbl Oct 24, 2019
015b383
Updated file names and naming conventions inside files
mstfbl Oct 24, 2019
20b29c0
Update nimbusml.pyproj
mstfbl Oct 24, 2019
0a9cae7
Updated usage infos of find_http_urls.py and change_to_https.py
mstfbl Oct 24, 2019
18b824e
Updated find_http_urls.py and change_to_https.py
mstfbl Oct 24, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions src/python/tools/changeHttpURLsToHttps.py → ...python/tools/change_http_urls_to_https.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,9 @@
# -------------------------------------------------------------------------

# Converts all valid HTTP links to HTTPS, where the fed
# HTTP links are found in Report_AlterableUrls_FindHttpURLs.csv, which
# is generated by FindHttpURLs.py
# usage: python3 changeHttpURLsToHttps.py [PATH_TO_Report_FindHttpURLs.txt] [PATH_TO_ROOT_OF_NIMBUSML_DIRECTORY]
# output: Report_ReplaceHttpsURLs.txt
# HTTP links are found in report_alterable_urls_find_http_urls.csv, which
# is generated by find_http_urls.py
# usage: python3 change_http_urls_to_https.py [PATH_TO_report_alterable_urls_find_http_urls.csv] [PATH_TO_ROOT_OF_NIMBUSML_DIRECTORY]
Comment thread
mstfbl marked this conversation as resolved.
Outdated

import sys
import os
Expand Down Expand Up @@ -36,7 +35,7 @@ def changeUrls(pathToReportCsv, pathToRootDirectory):

def main():
if len(sys.argv) < 3:
print("Usage: python3 changeHttpURLsToHttps.py [PATH_TO_Report_FindHttpURLs.txt] [PATH_TO_ORIGINAL_NIMBUSML_DIRECTORY]")
print("Usage: python3 change_http_urls_to_https.py [PATH_TO_report_alterable_urls_find_http_urls.csv] [PATH_TO_ORIGINAL_NIMBUSML_DIRECTORY]")
exit(1)
changeUrls(sys.argv[1], sys.argv[2])

Expand Down
12 changes: 6 additions & 6 deletions src/python/tools/findHttpURLs.py → src/python/tools/find_http_urls.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,8 @@

# Finds all HTTP URLs found in the NimbusML repository
# Converts all valid HTTP links to HTTPS
# Usage: python3 findHttpURLs.py [PATH_TO_NimbusML_REPOSITORY]
# Output: Report_AlterableUrls_FindHttpURLs.csv, [Report_NonAlterableUrls_FindHttpURLs.csv, Report_InvalidUrls_FindHttpURLs.csv]
# Usage: python3 find_http_urls.py [PATH_TO_NimbusML_REPOSITORY]
Comment thread
mstfbl marked this conversation as resolved.
Outdated
# Output: report_alterable_urls_find_http_urls.csv, report_non_alterable_urls_find_http_urls.csv, report_invalid_urls_find_http_urls.csv

# Required non-standard pip library: urlextract

Expand Down Expand Up @@ -73,19 +73,19 @@ def findHttpUrls(searchRootDirectory):
makeReports(alterableUrlsStore, nonAlterableUrlsStore, invalidUrlsStore)

def makeReports(alterableUrlsStore, nonAlterableUrlsStore, invalidUrlsStore):
with open('Report_AlterableUrls_FindHttpURLs.csv', mode='w', newline='') as csv_file:
with open('report_alterable_urls_find_http_urls.csv', mode='w', newline='') as csv_file:
Comment thread
mstfbl marked this conversation as resolved.
Outdated
writer1 = csv.writer(csv_file, delimiter='\t', quotechar='|', quoting=csv.QUOTE_MINIMAL)
writer1.writerow(["url", "relativeFilepath"])
for urlKey in alterableUrlsStore:
for fileValue in alterableUrlsStore[urlKey]:
writer1.writerow([urlKey, fileValue])
with open('Report_NonAlterableUrls_FindHttpURLs.csv', mode='w', newline='') as csv_file:
with open('report_non_alterable_urls_find_http_urls.csv', mode='w', newline='') as csv_file:
Comment thread
mstfbl marked this conversation as resolved.
Outdated
writer2 = csv.writer(csv_file, delimiter='\t', quotechar='|', quoting=csv.QUOTE_MINIMAL)
writer2.writerow(["url", "relativeFilepath"])
for urlKey in nonAlterableUrlsStore:
for fileValue in nonAlterableUrlsStore[urlKey]:
writer2.writerow([urlKey, fileValue])
with open('Report_InvalidUrls_FindHttpURLs.csv', mode='w', newline='') as csv_file:
with open('report_invalid_urls_find_http_urls.csv', mode='w', newline='') as csv_file:
Comment thread
mstfbl marked this conversation as resolved.
Outdated
writer3 = csv.writer(csv_file, delimiter='\t', quotechar='|', quoting=csv.QUOTE_MINIMAL)
writer3.writerow(["url", "relativeFilepath"])
for urlKey in invalidUrlsStore:
Expand All @@ -95,7 +95,7 @@ def makeReports(alterableUrlsStore, nonAlterableUrlsStore, invalidUrlsStore):

def main():
if len(sys.argv) < 2:
print("Usage: python3 findHttpURLs.py [PATH_TO_NimbusML_REPOSITORY]")
print("Usage: python3 find_http_urls.py [PATH_TO_NimbusML_REPOSITORY]")
Comment thread
mstfbl marked this conversation as resolved.
Outdated
exit(1)
findHttpUrls(sys.argv[1])

Expand Down