Skip to content

Commit f6c1b81

Browse files
authored
Merge pull request #201 from American-Institutes-for-Research/HEA-819/people_per_household_reg_ex
Add petit commerce and related varitions to regex see HEA-819
2 parents 87b6921 + 7358b60 commit f6c1b81

3 files changed

Lines changed: 47 additions & 2 deletions

File tree

pipelines/assets/livelihood_activity.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -240,7 +240,7 @@ def get_livelihood_activity_regexes() -> list:
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"\(?(?P<additional_identifier>rainfed|irrigated|pluviale?|irriguée|submersion libre|submersion contrôlée|flottant)\)?",
242242
"unit_of_measure_pattern": r"(?P<unit_of_measure_id>[a-z]+)",
243-
"nbr_pattern": r"(?:n[b|o]r?)\.?",
243+
"nbr_pattern": r"(?:n[bo]?r?e?|no)\.?",
244244
"vendu_pattern": r"(?:quantité )?vendu(?:e|s|ss|es|ses)?",
245245
"separator_pattern": r" ?[:-]?",
246246
}

pipelines/assets/livelihood_activity_regexes.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -866,7 +866,7 @@
866866
"unit_multiple"
867867
],
868868
[
869-
"{product_pattern}{separator_pattern} {nbr_pattern} (?:people per hh|personnes par ménage|personnes par mènage|pers par mènage)",
869+
"{product_pattern}{separator_pattern} {nbr_pattern} (?:de )?(?:pers|personnes|people)(?: ?/ ?| par | per )(?:ménage|mènage|hh)",
870870
null,
871871
true,
872872
"people_per_household"

pipelines_tests/test_assets/test_livelihood_activity_regexes.json

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -894,5 +894,50 @@
894894
"product_id": "fish type 2 (dried)",
895895
"unit_of_measure_id": "kg",
896896
"attribute": "quantity_produced"
897+
},
898+
"petit commerce: nbre de personnes par mènage": {
899+
"is_start": true,
900+
"product_id": "petit commerce",
901+
"attribute": "people_per_household"
902+
},
903+
"petit commerce: nbr. pers par mènage": {
904+
"is_start": true,
905+
"product_id": "petit commerce",
906+
"attribute": "people_per_household"
907+
},
908+
"petit commerce: nb de personnes par ménage": {
909+
"is_start": true,
910+
"product_id": "petit commerce",
911+
"attribute": "people_per_household"
912+
},
913+
"petit commerce: nb de personnes/ménage": {
914+
"is_start": true,
915+
"product_id": "petit commerce",
916+
"attribute": "people_per_household"
917+
},
918+
"petit commerce: nbr de personnes par ménage": {
919+
"is_start": true,
920+
"product_id": "petit commerce",
921+
"attribute": "people_per_household"
922+
},
923+
"petit commerce: nbr. personnes par ménage": {
924+
"is_start": true,
925+
"product_id": "petit commerce",
926+
"attribute": "people_per_household"
927+
},
928+
"petit commerce: nb. personnes par ménage": {
929+
"is_start": true,
930+
"product_id": "petit commerce",
931+
"attribute": "people_per_household"
932+
},
933+
"petty trade: no. people per hh": {
934+
"is_start": true,
935+
"product_id": "petty trade",
936+
"attribute": "people_per_household"
937+
},
938+
"petty trade: nbr. people per hh": {
939+
"is_start": true,
940+
"product_id": "petty trade",
941+
"attribute": "people_per_household"
897942
}
898943
}

0 commit comments

Comments
 (0)