From 98938e61260119e3a604e64ee2356a6001197a79 Mon Sep 17 00:00:00 2001 From: Lilleman auf Larv Date: Fri, 18 Sep 2026 18:39:04 +0200 Subject: [PATCH] Drop the SSA placeholder names and lowercase da, del and dos in Swedish surnames --- data-import/names-se.py | 2 +- data-import/names-us.py | 3 ++- data/en_US/first-name.tsv | 8 ++++---- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/data-import/names-se.py b/data-import/names-se.py index 0f7d82e..6ad6428 100644 --- a/data-import/names-se.py +++ b/data-import/names-se.py @@ -19,7 +19,7 @@ CACHE = Path(__file__).resolve().parent / "cache" SHEETS = {"f": "Tilltalsnamn kvinnor", "m": "Tilltalsnamn män"} SURNAMES = "Efternamn" NAME = re.compile(r"^[^\W\d_]{2,}([ '-][^\W\d_]{2,})*$") -PARTICLES = {"af", "av", "de", "den", "der", "di", "du", "la", "le", "van", "von"} +PARTICLES = {"af", "av", "da", "de", "del", "den", "der", "di", "dos", "du", "la", "le", "van", "von"} def cased(name): diff --git a/data-import/names-us.py b/data-import/names-us.py index 2f982e6..8e6d364 100644 --- a/data-import/names-us.py +++ b/data-import/names-us.py @@ -23,6 +23,7 @@ SURNAMES = "https://www2.census.gov/topics/genealogy/2010surnames/names.zip" OUT = Path(__file__).resolve().parent.parent / "data" / "en_US" CACHE = Path(__file__).resolve().parent / "cache" MC = re.compile(r"^Mc([a-z])") +PLACEHOLDERS = {"Baby", "Female", "Infant", "Male", "Notnamed", "Unknown", "Unnamed"} def csv_or_zip_rows(data, member): @@ -41,7 +42,7 @@ def csv_or_zip_rows(data, member): def given(data, from_year): counts = collections.Counter() for r in csv_or_zip_rows(data, r"yob\d{4}\.txt"): - if len(r) >= 4 and r[3].isdigit() and int(r[3]) >= from_year: + if len(r) >= 4 and r[3].isdigit() and int(r[3]) >= from_year and r[0] not in PLACEHOLDERS: counts[(r[0], r[1].lower())] += int(r[2]) return counts diff --git a/data/en_US/first-name.tsv b/data/en_US/first-name.tsv index 9d966bb..0b65378 100644 --- a/data/en_US/first-name.tsv +++ b/data/en_US/first-name.tsv @@ -379,7 +379,6 @@ Ayla f 23690 Aylin f 12970 Azalea f 7052 Azariah m 3910 -Baby m 6059 Bailee f 14798 Bailey f 102509 Bailey m 20062 @@ -468,6 +467,7 @@ Bobbie f 78660 Bobbie m 14570 Bobby f 8180 Bobby m 299694 +Bode m 3348 Bodhi m 8375 Bodie m 4314 Bonita f 35102 @@ -1674,7 +1674,6 @@ Imran m 3415 Ina f 15116 India f 21903 Inez f 22303 -Infant m 4133 Ingrid f 25835 Ira m 33974 Irene f 150081 @@ -2615,6 +2614,7 @@ Lynn f 180561 Lynn m 44787 Lynne f 61433 Lynnette f 15029 +Lynwood m 3349 Lyric f 17861 Lyric m 3810 Mabel f 24359 @@ -3274,6 +3274,7 @@ Ricky m 221617 Rico m 9313 Ridge m 5086 Rigoberto m 11018 +Rihanna f 5970 Rikki f 6846 Riley f 117947 Riley m 92931 @@ -3804,6 +3805,7 @@ Tylor m 7980 Tyquan m 3547 Tyra f 14416 Tyree m 13959 +Tyrel m 3354 Tyrell m 15575 Tyrese m 8673 Tyron m 7456 @@ -3814,8 +3816,6 @@ Tyson m 44397 Ulises m 10786 Ulysses m 13923 Unique f 7103 -Unknown f 9225 -Unknown m 8912 Uriah m 9786 Uriel m 17743 Urijah m 3365