larvit/fejkdata
3
0
Fork 0
Code Pull Requests Actions Activity

Load the whole shipped set where a test loaded one locale, and admit registered street and place names

Browse Source
This commit is contained in:
Lilleman auf Larv
2026-09-18 00:23:03 +02:00
parent 2127b3277c
commit 42c74b9b43
5 changed files with 43 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bench_test.go
+6 -6
View File
@@ -26,12 +26,12 @@ func benchPath(b *testing.B, dir, path string) {
} }
} }
func BenchmarkPerson(b *testing.B) { benchPath(b, "data/sv_SE", "person") } func BenchmarkPerson(b *testing.B) { benchPath(b, "data", "sv_SE.person") }
func BenchmarkAddress(b *testing.B) { benchPath(b, "data/sv_SE", "address") } func BenchmarkAddress(b *testing.B) { benchPath(b, "data", "sv_SE.address") }
func BenchmarkWord(b *testing.B) { benchPath(b, "data/sv_SE", "word") } func BenchmarkWord(b *testing.B) { benchPath(b, "data", "sv_SE.word") }
func BenchmarkCreditcard(b *testing.B) { benchPath(b, "data/misc", "creditcard") } func BenchmarkCreditcard(b *testing.B) { benchPath(b, "data", "misc.creditcard") }
func BenchmarkSSN(b *testing.B) { benchPath(b, "data/sv_SE", "ssn") } func BenchmarkSSN(b *testing.B) { benchPath(b, "data", "sv_SE.ssn") }
func BenchmarkUUIDv7(b *testing.B) { benchPath(b, "data/misc", "uuid") } func BenchmarkUUIDv7(b *testing.B) { benchPath(b, "data", "misc.uuid") }
func tmpData(b *testing.B, name, body string) string { func tmpData(b *testing.B, name, body string) string {
b.Helper() b.Helper()
cmd/fejkdata/main_test.go
+4 -3
View File
@@ -14,6 +14,7 @@ import (
const ( const (
svSE = "../../data/sv_SE" svSE = "../../data/sv_SE"
enUS = "../../data/en_US" enUS = "../../data/en_US"
misc = "../../data/misc"
) )
func runOut(args ...string) (int, string, string) { func runOut(args ...string) (int, string, string) {
@@ -405,14 +406,14 @@ func TestRunTemplateMisuse(t *testing.T) {
} }
func TestRunNoShippedData(t *testing.T) { func TestRunNoShippedData(t *testing.T) {
code, list, errb := runOut("--no-shipped-data", "-d", svSE, "--list") code, list, errb := runOut("--no-shipped-data", "-d", misc, "--list")
if code != 0 { if code != 0 {
t.Fatalf("run = %d, stderr=%q", code, errb) t.Fatalf("run = %d, stderr=%q", code, errb)
} }
if strings.Contains(list, "en_US") || !strings.Contains(list, "person\n") { if strings.Contains(list, "sv_SE") || !strings.Contains(list, "uuid\n") {
t.Errorf("--no-shipped-data --list = %q, want only the given dir", list) t.Errorf("--no-shipped-data --list = %q, want only the given dir", list)
} }
code, out, _ := runOut("--no-shipped-data", "-d", svSE, "-s", "3", "person") code, out, _ := runOut("--no-shipped-data", "-d", misc, "-s", "3", "uuid")
if code != 0 || strings.TrimSpace(out) == "" { if code != 0 || strings.TrimSpace(out) == "" {
t.Errorf("run = %d, out=%q", code, out) t.Errorf("run = %d, out=%q", code, out)
} }
data_test.go
+27 -28
View File
@@ -51,14 +51,13 @@ func TestShippedDataCategories(t *testing.T) {
regexp.MustCompile(`^\d{1,3}( \d{3})?(,\d{2})? kr$`)}, regexp.MustCompile(`^\d{1,3}( \d{3})?(,\d{2})? kr$`)},
} }
en := newGenerator(t, "data/en_US", WithSeed(1)) f := newGenerator(t, "data", WithSeed(1))
sv := newGenerator(t, "data/sv_SE", WithSeed(1))
for _, c := range cases { for _, c := range cases {
for i := 0; i < 200; i++ { for i := 0; i < 200; i++ {
if v := fake(t, en, c.path); !c.en.MatchString(v) { if v := fake(t, f, "en_US."+c.path); !c.en.MatchString(v) {
t.Fatalf("en_US %s = %q, want %s", c.path, v, c.en) t.Fatalf("en_US %s = %q, want %s", c.path, v, c.en)
} }
if v := fake(t, sv, c.path); !c.sv.MatchString(v) { if v := fake(t, f, "sv_SE."+c.path); !c.sv.MatchString(v) {
t.Fatalf("sv_SE %s = %q, want %s", c.path, v, c.sv) t.Fatalf("sv_SE %s = %q, want %s", c.path, v, c.sv)
} }
} }
@@ -134,8 +133,8 @@ func TestShippedMiscReferenceData(t *testing.T) {
// TestSwedishPersonNamesHaveNoTripleLetter pins an orthographic rule the shape // TestSwedishPersonNamesHaveNoTripleLetter pins an orthographic rule the shape
// regexes miss: no generated name repeats a character three times over. // regexes miss: no generated name repeats a character three times over.
func TestSwedishPersonNamesHaveNoTripleLetter(t *testing.T) { func TestSwedishPersonNamesHaveNoTripleLetter(t *testing.T) {
f := newGenerator(t, "data/sv_SE", WithSeed(11)) f := newGenerator(t, "data", WithSeed(11))
for _, path := range []string{"person", "person.last"} { for _, path := range []string{"sv_SE.person", "sv_SE.person.last"} {
for i := 0; i < 20000; i++ { for i := 0; i < 20000; i++ {
name := fake(t, f, path) name := fake(t, f, path)
r := []rune(name) r := []rune(name)
@@ -152,10 +151,10 @@ func TestSwedishPersonNamesHaveNoTripleLetter(t *testing.T) {
// is a real calendar date (so month-length variants never emit e.g. Apr 31 or // is a real calendar date (so month-length variants never emit e.g. Apr 31 or
// Feb 30) and the trailing digit is a valid Luhn checksum over the other nine. // Feb 30) and the trailing digit is a valid Luhn checksum over the other nine.
func TestSwedishPersonnummer(t *testing.T) { func TestSwedishPersonnummer(t *testing.T) {
sv := newGenerator(t, "data/sv_SE", WithSeed(1)) sv := newGenerator(t, "data", WithSeed(1))
sawLongMonthEnd := false sawLongMonthEnd := false
for i := 0; i < 2000; i++ { for i := 0; i < 2000; i++ {
v := fake(t, sv, "ssn") v := fake(t, sv, "sv_SE.ssn")
d := digitsOnly(v) d := digitsOnly(v)
if len(d) != 10 { if len(d) != 10 {
t.Fatalf("ssn %q has %d digits, want 10", v, len(d)) t.Fatalf("ssn %q has %d digits, want 10", v, len(d))
@@ -176,49 +175,49 @@ func TestSwedishPersonnummer(t *testing.T) {
} }
func TestShippedSwedishPhone(t *testing.T) { func TestShippedSwedishPhone(t *testing.T) {
f := newGenerator(t, "data/sv_SE", WithSeed(11)) f := newGenerator(t, "data", WithSeed(11))
re := regexp.MustCompile(`^0\d{1,2}-\d{3} \d{2} \d{2}$`) re := regexp.MustCompile(`^0\d{1,2}-\d{3} \d{2} \d{2}$`)
for i := 0; i < 50; i++ { for i := 0; i < 50; i++ {
if n := fake(t, f, "phone"); !re.MatchString(n) { if n := fake(t, f, "sv_SE.phone"); !re.MatchString(n) {
t.Fatalf("phone %q does not match %s", n, re) t.Fatalf("phone %q does not match %s", n, re)
} }
} }
} }
func TestShippedSwedishAddress(t *testing.T) { func TestShippedSwedishAddress(t *testing.T) {
f := newGenerator(t, "data/sv_SE", WithSeed(3)) f := newGenerator(t, "data", WithSeed(3))
digit := regexp.MustCompile(`\d`) digit := regexp.MustCompile(`\d`)
for i := 0; i < 30; i++ { for i := 0; i < 30; i++ {
a := fake(t, f, "address") a := fake(t, f, "sv_SE.address")
if !regexp.MustCompile(`\n`).MatchString(a) || !digit.MatchString(a) { if !regexp.MustCompile(`\n`).MatchString(a) || !digit.MatchString(a) {
t.Fatalf("address %q is not a multi-line address with a number", a) t.Fatalf("address %q is not a multi-line address with a number", a)
} }
} }
locality := regexp.MustCompile(`^\p{L}+( \p{L}+)*$`) locality := regexp.MustCompile(`^\p{L}+([ -]\p{L}+)*$`)
for i := 0; i < 30; i++ { for i := 0; i < 30; i++ {
if c := fake(t, f, "address.locality"); !locality.MatchString(c) { if c := fake(t, f, "sv_SE.address.locality"); !locality.MatchString(c) {
t.Fatalf("locality %q is not a Swedish place name", c) t.Fatalf("locality %q is not a Swedish place name", c)
} }
} }
} }
func TestShippedPersonHasParts(t *testing.T) { func TestShippedPersonHasParts(t *testing.T) {
for _, dir := range []string{"data/sv_SE", "data/en_US"} { f := newGenerator(t, "data", WithSeed(7))
f := newGenerator(t, dir, WithSeed(7)) for _, path := range []string{"sv_SE.person", "en_US.person"} {
for i := 0; i < 30; i++ { for i := 0; i < 30; i++ {
if name := fake(t, f, "person"); len(name) < 3 || !regexp.MustCompile(`\S \S`).MatchString(name) { if name := fake(t, f, path); len(name) < 3 || !regexp.MustCompile(`\S \S`).MatchString(name) {
t.Fatalf("%s person %q lacks first and last name", dir, name) t.Fatalf("%s %q lacks first and last name", path, name)
} }
} }
} }
} }
func TestShippedUSPhone(t *testing.T) { func TestShippedUSPhone(t *testing.T) {
f := newGenerator(t, "data/en_US", WithSeed(11)) f := newGenerator(t, "data", WithSeed(11))
re := regexp.MustCompile(`^(\(\d{3}\) \d{3}-\d{4}|\d{3}-\d{3}-\d{4})$`) re := regexp.MustCompile(`^(\(\d{3}\) \d{3}-\d{4}|\d{3}-\d{3}-\d{4})$`)
for i := 0; i < 50; i++ { for i := 0; i < 50; i++ {
if n := fake(t, f, "phone"); !re.MatchString(n) { if n := fake(t, f, "en_US.phone"); !re.MatchString(n) {
t.Fatalf("phone %q does not match %s", n, re) t.Fatalf("phone %q does not match %s", n, re)
} }
} }
@@ -270,11 +269,11 @@ func luhnValid(s string) bool {
// tests so shipped name lists can grow without re-enumerating them here. // tests so shipped name lists can grow without re-enumerating them here.
var swedishName = regexp.MustCompile(`^\p{L}+([ -]\p{L}+)*$`) var swedishName = regexp.MustCompile(`^\p{L}+([ -]\p{L}+)*$`)
func TestShippedStreetComposition(t *testing.T) { func TestShippedStreetIsARegisteredName(t *testing.T) {
// street is a choice of composed {first}{last} templates and literal names. f := newGenerator(t, "data", WithSeed(5))
f := newGenerator(t, "data/sv_SE", WithSeed(5)) street := regexp.MustCompile(`^\p{L}[\p{L}\d:.-]*([ -][\p{L}\d:.-]+)*$`)
for i := 0; i < 300; i++ { for i := 0; i < 300; i++ {
if s := fake(t, f, "address.street"); !swedishName.MatchString(s) { if s := fake(t, f, "sv_SE.address.street"); !street.MatchString(s) {
t.Fatalf("street %q is not a Swedish street name", s) t.Fatalf("street %q is not a Swedish street name", s)
} }
} }
@@ -283,9 +282,9 @@ func TestShippedStreetComposition(t *testing.T) {
func TestShippedLastNameComposition(t *testing.T) { func TestShippedLastNameComposition(t *testing.T) {
// last is a choice of patronymic {first}sson templates, compound // last is a choice of patronymic {first}sson templates, compound
// {first}{last} templates and literal surnames. // {first}{last} templates and literal surnames.
f := newGenerator(t, "data/sv_SE", WithSeed(6)) f := newGenerator(t, "data", WithSeed(6))
for i := 0; i < 300; i++ { for i := 0; i < 300; i++ {
if s := fake(t, f, "person.last"); !swedishName.MatchString(s) { if s := fake(t, f, "sv_SE.person.last"); !swedishName.MatchString(s) {
t.Fatalf("last name %q is not a Swedish surname", s) t.Fatalf("last name %q is not a Swedish surname", s)
} }
} }
@@ -293,10 +292,10 @@ func TestShippedLastNameComposition(t *testing.T) {
func TestShippedStreetNumberFormats(t *testing.T) { func TestShippedStreetNumberFormats(t *testing.T) {
// Reachable via a hyphenated path; covers all five weighted number variants. // Reachable via a hyphenated path; covers all five weighted number variants.
f := newGenerator(t, "data/sv_SE", WithSeed(8)) f := newGenerator(t, "data", WithSeed(8))
re := regexp.MustCompile(`^[1-9]\d{0,2}[A-Z]?$`) re := regexp.MustCompile(`^[1-9]\d{0,2}[A-Z]?$`)
for i := 0; i < 300; i++ { for i := 0; i < 300; i++ {
if n := fake(t, f, "address.street-number"); !re.MatchString(n) { if n := fake(t, f, "sv_SE.address.street-number"); !re.MatchString(n) {
t.Fatalf("street-number %q does not match %s", n, re) t.Fatalf("street-number %q does not match %s", n, re)
} }
} }
fejkdata_test.go
+4 -4
View File
@@ -64,18 +64,18 @@ func TestNewReportsAnEntropyFailure(t *testing.T) {
} }
func TestWithSeedIsDeterministic(t *testing.T) { func TestWithSeedIsDeterministic(t *testing.T) {
a, b := newGenerator(t, "data/sv_SE", WithSeed(42)), newGenerator(t, "data/sv_SE", WithSeed(42)) a, b := newGenerator(t, "data", WithSeed(42)), newGenerator(t, "data", WithSeed(42))
for i := 0; i < 50; i++ { for i := 0; i < 50; i++ {
if x, y := fake(t, a, "person"), fake(t, b, "person"); x != y { if x, y := fake(t, a, "sv_SE.person"), fake(t, b, "sv_SE.person"); x != y {
t.Fatalf("same seed diverged at %d: %q != %q", i, x, y) t.Fatalf("same seed diverged at %d: %q != %q", i, x, y)
} }
} }
} }
func TestDifferentSeedsDiffer(t *testing.T) { func TestDifferentSeedsDiffer(t *testing.T) {
a, b := newGenerator(t, "data/en_US", WithSeed(1)), newGenerator(t, "data/en_US", WithSeed(2)) a, b := newGenerator(t, "data", WithSeed(1)), newGenerator(t, "data", WithSeed(2))
for i := 0; i < 50; i++ { for i := 0; i < 50; i++ {
if fake(t, a, "person") != fake(t, b, "person") { if fake(t, a, "en_US.person") != fake(t, b, "en_US.person") {
return return
} }
} }
path_test.go
+2 -2
View File
@@ -130,8 +130,8 @@ func TestPathKeyIsUnambiguous(t *testing.T) {
// single-variant choice always picks the same item, so it needs no every-variant // single-variant choice always picks the same item, so it needs no every-variant
// guard and the error can name the field that is missing. // guard and the error can name the field that is missing.
func TestMissingFieldNamesItself(t *testing.T) { func TestMissingFieldNamesItself(t *testing.T) {
f := newGenerator(t, "data/sv_SE", WithSeed(1)) f := newGenerator(t, "data", WithSeed(1))
_, err := f.Fake("person.typo") _, err := f.Fake("sv_SE.person.typo")
if err == nil || !strings.Contains(err.Error(), `no field "typo"`) { if err == nil || !strings.Contains(err.Error(), `no field "typo"`) {
t.Errorf("Fake(person.typo) = %v, want it to name the missing field", err) t.Errorf("Fake(person.typo) = %v, want it to name the missing field", err)
} }