improve migration scripts for python3

open-data · Jan 31, 2025 · bc06c0d · bc06c0d
1 parent 556d633
commit bc06c0d
Showing 8 changed files with 48 additions and 40 deletions.
diff --git a/bin/migrate/migrate_briefingt_2025_02.py b/bin/migrate/migrate_briefingt_2025_02.py
@@ -6,9 +6,9 @@
 for PCO sub-organizations into PCO organization
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -20,15 +20,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 for line in in_csv:

diff --git a/bin/migrate/migrate_briefingt_nil_2025_12.py → bin/migrate/migrate_briefingt_nil_2025_02.py b/bin/migrate/migrate_briefingt_nil_2025_12.py → bin/migrate/migrate_briefingt_nil_2025_02.py
@@ -8,9 +8,9 @@
 reporting_period will be ignored
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -22,15 +22,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 data = []

diff --git a/bin/migrate/migrate_hospitalityq_2025_02.py b/bin/migrate/migrate_hospitalityq_2025_02.py
@@ -6,9 +6,9 @@
 for PCO sub-organizations into PCO organization
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -20,15 +20,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 for line in in_csv:

diff --git a/bin/migrate/migrate_hospitalityq_nil_2025_02.py b/bin/migrate/migrate_hospitalityq_nil_2025_02.py
@@ -8,9 +8,9 @@
 will be ignored
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -22,15 +22,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 data = []

diff --git a/bin/migrate/migrate_qpnotes_2025_02.py b/bin/migrate/migrate_qpnotes_2025_02.py
@@ -6,9 +6,9 @@
 for PCO sub-organizations into PCO organization
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -20,15 +20,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 for line in in_csv:

diff --git a/bin/migrate/migrate_travela_2025_02.py b/bin/migrate/migrate_travela_2025_02.py
@@ -6,9 +6,9 @@
 for PCO sub-organizations into PCO organization
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -20,15 +20,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 for line in in_csv:

diff --git a/bin/migrate/migrate_travelq_2025_02.py b/bin/migrate/migrate_travelq_2025_02.py
@@ -6,9 +6,9 @@
 for PCO sub-organizations into PCO organization
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -20,15 +20,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 for line in in_csv:

diff --git a/bin/migrate/migrate_travelq_nil_2025_02.py b/bin/migrate/migrate_travelq_nil_2025_02.py
@@ -8,9 +8,9 @@
 will be ignored
 """
 
-import unicodecsv
-import sys
 import codecs
+import csv
+import sys
 
 
 sub_orgs = [
@@ -22,15 +22,16 @@
     'ql-lq',
     'srp-rsp',
     ]
+
 PCO = {
     'owner_org': 'pco-bcp',
     'owner_org_title': 'Privy Council Office | Bureau du Conseil privé',
     }
 
-assert sys.stdin.read(3) == codecs.BOM_UTF8
+assert sys.stdin.buffer.read(3) == codecs.BOM_UTF8, "Input file does not contain the UTF-8 BOM."
 
-in_csv = unicodecsv.DictReader(sys.stdin, encoding='utf-8')
-out_csv = unicodecsv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames, encoding='utf-8')
+in_csv = csv.DictReader(sys.stdin)
+out_csv = csv.DictWriter(sys.stdout, fieldnames=in_csv.fieldnames)
 out_csv.writeheader()
 
 data = []