Skip to content

Commit a71436d

Browse files
committed
Add regex pattern for men, women .. see HEA-809
1 parent d006329 commit a71436d

3 files changed

Lines changed: 53 additions & 1 deletion

File tree

pipelines/assets/livelihood_activity.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -239,6 +239,7 @@ def get_livelihood_activity_regexes() -> list:
239239
"product_pattern": r"(?P<product_id>[a-zà-ÿ][a-zà-ÿ1-9',/ \.\>\-\(\)]+?)",
240240
"season_pattern": r"(?P<season>season [12]|saison [12]|[12][a-z] season||[12][a-zà-ÿ] saison|r[eé]colte principale|principale r[eé]colte|gu|deyr+?)", # NOQA: E501
241241
"additional_identifier_pattern": r"\(?(?P<additional_identifier>rainfed|irrigated|pluviale?|irriguée|submersion libre|submersion contrôlée|flottant)\)?",
242+
"age_gender_pattern": r"(?P<additional_identifier>filles/garçons|garçons/filles|garcons/filles|filles/garcons|boys/girls|girls/boys|men|hommes|women|femmes|boys|garcons|garçons|girls|filles)",
242243
"unit_of_measure_pattern": r"(?P<unit_of_measure_id>[a-z]+)",
243244
"nbr_pattern": r"(?:n[b|o]r?)\.?",
244245
"vendu_pattern": r"(?:quantité )?vendu(?:e|s|ss|es|ses)?",

pipelines/assets/livelihood_activity_regexes.json

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,12 @@
5555
true,
5656
null
5757
],
58+
[
59+
"{age_gender_pattern}",
60+
null,
61+
false,
62+
null
63+
],
5864
[
5965
"(?:other purchases?|autres? achats?|achats?):?",
6066
"OtherPurchase",

pipelines_tests/test_assets/test_livelihood_activity_regexes.json

Lines changed: 46 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -865,5 +865,50 @@
865865
"product_id": "fish type 2 (dried)",
866866
"unit_of_measure_id": "kg",
867867
"attribute": "quantity_produced"
868-
}
868+
},
869+
"men": {
870+
"additional_identifier": "men"
871+
},
872+
"women": {
873+
"additional_identifier": "women"
874+
},
875+
"boys": {
876+
"additional_identifier": "boys"
877+
},
878+
"girls": {
879+
"additional_identifier": "girls"
880+
},
881+
"hommes": {
882+
"additional_identifier": "hommes"
883+
},
884+
"femmes": {
885+
"additional_identifier": "femmes"
886+
},
887+
"garcons": {
888+
"additional_identifier": "garcons"
889+
},
890+
"garçons": {
891+
"additional_identifier": "garçons"
892+
},
893+
"filles": {
894+
"additional_identifier": "filles"
895+
},
896+
"filles/garçons": {
897+
"additional_identifier": "filles/garçons"
898+
},
899+
"garçons/filles": {
900+
"additional_identifier": "garçons/filles"
901+
},
902+
"garcons/filles": {
903+
"additional_identifier": "garcons/filles"
904+
},
905+
"filles/garcons": {
906+
"additional_identifier": "filles/garcons"
907+
},
908+
"boys/girls": {
909+
"additional_identifier": "boys/girls"
910+
},
911+
"girls/boys": {
912+
"additional_identifier": "girls/boys"
913+
}
869914
}

0 commit comments

Comments
 (0)