oppi.li
bnewbold.net
-40
automod/keyword/identifier_regex.go
-40
automod/keyword/identifier_regex.go
···
1
-
package keyword
2
-
3
-
import (
4
-
"regexp"
5
-
"strings"
6
-
)
7
-
8
-
// regexes taken from: https://github.com/Blank-Cheque/Slurs
9
-
var explicitKeywordRegexes = []*regexp.Regexp{
10
-
// "chink"
11
-
regexp.MustCompile("\\b[cĆćĈĉČčĊċÇçḈḉȻȼꞒꞓꟄꞔƇƈɕ][hĤĥȞȟḦḧḢḣḨḩḤḥḪḫH̱ẖĦħⱧⱨꞪɦꞕΗНн][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?\\b"),
12
-
// "coon"
13
-
regexp.MustCompile("\\b[cĆćĈĉČčĊċÇçḈḉȻȼꞒꞓꟄꞔƇƈɕ][ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0]{2}[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?\\b"),
14
-
// "faggot"
15
-
regexp.MustCompile("\\b[fḞḟƑƒꞘꞙᵮᶂ][aÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ@4][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]{1,2}([ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅiÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][tŤťṪṫŢţṬṭȚțṰṱṮṯŦŧȾⱦ ƬƭƮʈT̈ẗᵵƫȶ]{1,2}([rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾế ỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ])?)?[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?\\b"),
16
-
// "kike"
17
-
regexp.MustCompile("\\b[kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌyÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ][kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝ ĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ]([rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫ ɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ])?[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]*\\b"),
18
-
// "nigger"
19
-
regexp.MustCompile("\\b[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌoÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏІіa4ÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]{2}(l[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩ e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ]t|[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅaÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ ]?|n[ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]|[a4ÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚ Ａａ]?)?[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?\\b"),
20
-
// "nigger", ignoring word-breaks
21
-
regexp.MustCompile("[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌoÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ ó̩ƟɵꝊꝋꝌꝍⱺＯｏІіa4ÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]{2}(l[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩ è̩É̩é̩ᶒⱸꬴꬳＥｅ]t|[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ])[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
22
-
// "tpranny"
23
-
regexp.MustCompile("\\b[tŤťṪṫŢţṬṭȚțṰṱṮṯŦŧȾⱦƬƭƮʈT̈ẗᵵƫȶ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][aÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ4]+[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ]{1,2}([iÍíi̇́Ììi̇̀ĬĭÎîǏ ǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ]|[yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễ ỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ])[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?\\b"),
24
-
}
25
-
26
-
// For a small set of frequently-abused explicit keywords, checks for a large number of possible variants and "l33t-speak" variations of the keyword. This is intended to be used with no-whitespace identifiers, like DIDs, handle, rkeys.
27
-
//
28
-
// This is a port of the 'hasExplicitSlur' function from the `@atproto/pds` TypeScript package.
29
-
func IdentifierContainsExplicitKeyword(raw string) bool {
30
-
compact := raw
31
-
for _, c := range []string{".", "-", "_"} {
32
-
compact = strings.ReplaceAll(compact, c, "")
33
-
}
34
-
for _, r := range explicitKeywordRegexes {
35
-
if r.MatchString(raw) || r.MatchString(compact) {
36
-
return true
37
-
}
38
-
}
39
-
return false
40
-
}
-35
automod/keyword/identifier_regex_test.go
-35
automod/keyword/identifier_regex_test.go
···
1
-
package keyword
2
-
3
-
import (
4
-
"testing"
5
-
6
-
"github.com/stretchr/testify/assert"
7
-
)
8
-
9
-
func TestIdentifierContainsExplicitKeyword(t *testing.T) {
10
-
assert := assert.New(t)
11
-
12
-
fixtures := []struct {
13
-
text string
14
-
out bool
15
-
}{
16
-
{out: false, text: ""},
17
-
{out: false, text: "hello"},
18
-
{out: true, text: "chink"},
19
-
{out: true, text: "coon"},
20
-
{out: true, text: "faggot"},
21
-
{out: true, text: "kike"},
22
-
{out: true, text: "nigger"},
23
-
{out: true, text: "tranny"},
24
-
{out: true, text: "faggot.bsky.social"},
25
-
{out: true, text: "fagg.ot"},
26
-
{out: true, text: "niggers.bsky.social"},
27
-
{out: true, text: "n.igger.bsky.social"},
28
-
{out: true, text: "n-igger.bsky.social"},
29
-
{out: true, text: "n_igger.bsky.social"},
30
-
}
31
-
32
-
for _, fix := range fixtures {
33
-
assert.Equal(fix.out, IdentifierContainsExplicitKeyword(fix.text))
34
-
}
35
-
}
+10
automod/keyword/keyword.go
+10
automod/keyword/keyword.go
+20
automod/keyword/keyword_test.go
+20
automod/keyword/keyword_test.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"testing"
5
+
6
+
"github.com/stretchr/testify/assert"
7
+
)
8
+
9
+
func TestTokenInSet(t *testing.T) {
10
+
assert := assert.New(t)
11
+
12
+
keywords := []string{
13
+
"example",
14
+
"bunch",
15
+
}
16
+
17
+
assert.True(TokenInSet("example", keywords))
18
+
assert.False(TokenInSet("Example", keywords))
19
+
assert.False(TokenInSet("elephant", keywords))
20
+
}
+13
automod/keyword/slugify.go
+13
automod/keyword/slugify.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"strings"
5
+
"regexp"
6
+
)
7
+
8
+
var nonSlugChars = regexp.MustCompile(`[^\pL\pN]+`)
9
+
10
+
// Takes an arbitrary string (eg, an identifier or free-form text) and returns a version with all non-letter, non-digit characters removed, and all lower-case
11
+
func Slugify(orig string) string {
12
+
return strings.ToLower(nonSlugChars.ReplaceAllString(orig, ""))
13
+
}
+31
automod/keyword/slur_regex.go
+31
automod/keyword/slur_regex.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"regexp"
5
+
)
6
+
7
+
// regexes taken from: https://github.com/Blank-Cheque/Slurs
8
+
var explicitSlurRegexes = map[string]*regexp.Regexp{
9
+
"chink": regexp.MustCompile("[cĆćĈĉČčĊċÇçḈḉȻȼꞒꞓꟄꞔƇƈɕ][hĤĥȞȟḦḧḢḣḨḩḤḥḪḫH̱ẖĦħⱧⱨꞪɦꞕΗНн][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
10
+
// modified to not match "cocoon", "raccoon", "racoon", or "tycoon"
11
+
"coon": regexp.MustCompile("(^|[^cayo])[cĆćĈĉČčĊċÇçḈḉȻȼꞒꞓꟄꞔƇƈɕ][ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0]{2}[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
12
+
"faggot": regexp.MustCompile("[fḞḟƑƒꞘꞙᵮᶂ][aÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ@4][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]{1,2}([ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅiÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][tŤťṪṫŢţṬṭȚțṰṱṮṯŦŧȾⱦ ƬƭƮʈT̈ẗᵵƫȶ]{1,2}([rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾế ỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ])?)?[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
13
+
"kike": regexp.MustCompile("[kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌyÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ][kḰḱǨǩĶķḲḳḴḵƘƙⱩⱪᶄꝀꝁꝂꝃꝄꝅꞢꞣ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝ ĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ]([rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫ ɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ])?[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]*"),
14
+
// modified to not match "snigger"
15
+
"nigger": regexp.MustCompile("(^|[^s])[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ][iÍíi̇́Ììi̇̀ĬĭÎîǏǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌoÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏІіa4ÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]{2}([e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅaÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ ]?|n[ÓóÒòŎŏÔôỐốỒồỖỗỔổǑǒÖöȪȫŐőÕõṌṍṎṏȬȭȮȯO͘o͘ȰȱØøǾǿǪǫǬǭŌōṒṓṐṑỎỏȌȍȎȏƠơỚớỜờỠỡỞởỢợỌọỘộO̩o̩Ò̩ò̩Ó̩ó̩ƟɵꝊꝋꝌꝍⱺＯｏ0][gǴǵĞğĜĝǦǧĠġG̃g̃ĢģḠḡǤǥꞠꞡƓɠᶃꬶＧｇqꝖꝗꝘꝙɋʠ]|[a4ÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚ Ａａ])[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
16
+
"tranny": regexp.MustCompile("[tŤťṪṫŢţṬṭȚțṰṱṮṯŦŧȾⱦƬƭƮʈT̈ẗᵵƫȶ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ][aÁáÀàĂăẮắẰằẴẵẲẳÂâẤấẦầẪẫẨẩǍǎÅåǺǻÄäǞǟÃãȦȧǠǡĄąĄ́ą́Ą̃ą̃ĀāĀ̀ā̀ẢảȀȁA̋a̋ȂȃẠạẶặẬậḀḁȺⱥꞺꞻᶏẚＡａ4]+[nŃńǸǹŇňÑñṄṅŅņṆṇṊṋṈṉN̈n̈ƝɲŊŋꞐꞑꞤꞥᵰᶇɳȵꬻꬼИиПпＮｎ]{1,2}([iÍíi̇́Ììi̇̀ĬĭÎîǏ ǐÏïḮḯĨĩi̇̃ĮįĮ́į̇́Į̃į̇̃ĪīĪ̀ī̀ỈỉȈȉI̋i̋ȊȋỊịꞼꞽḬḭƗɨᶖİiIıＩｉ1lĺľļḷḹl̃ḽḻłŀƚꝉⱡɫɬꞎꬷꬸꬹᶅɭȴＬｌ][e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ]|[yÝýỲỳŶŷY̊ẙŸÿỸỹẎẏȲȳỶỷỴỵɎɏƳƴỾỿ]|[e3ЄєЕеÉéÈèĔĕÊêẾếỀềỄễ ỂểÊ̄ê̄Ê̌ê̌ĚěËëẼẽĖėĖ́ė́Ė̃ė̃ȨȩḜḝĘęĘ́ę́Ę̃ę̃ĒēḖḗḔḕẺẻȄȅE̋e̋ȆȇẸẹỆệḘḙḚḛɆɇE̩e̩È̩è̩É̩é̩ᶒⱸꬴꬳＥｅ][rŔŕŘřṘṙŖŗȐȑȒȓṚṛṜṝṞṟR̃r̃ɌɍꞦꞧⱤɽᵲᶉꭉ])[sŚśṤṥŜŝŠšṦṧṠṡŞşṢṣṨṩȘșS̩s̩ꞨꞩⱾȿꟅʂᶊᵴ]?"),
17
+
}
18
+
19
+
// For a small set of frequently-abused explicit slurs, checks for a of permissive set of "l33t-speak" variations of the keyword. This is intended to be used with pre-processed "slugs", which are strings with all whitespace, punctuation, and other characters removed. These could be pre-processed identifiers (like handles or record keys), or pre-processed free-form text.
20
+
//
21
+
// If there is a match, returns a plan-text version of the slur.
22
+
//
23
+
// This is a loose port of the 'hasExplicitSlur' function from the `@atproto/pds` TypeScript package.
24
+
func SlugContainsExplicitSlur(raw string) string {
25
+
for word, r := range explicitSlurRegexes {
26
+
if r.MatchString(raw) {
27
+
return word
28
+
}
29
+
}
30
+
return ""
31
+
}
+66
automod/keyword/slur_regex_test.go
+66
automod/keyword/slur_regex_test.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"testing"
5
+
6
+
"github.com/stretchr/testify/assert"
7
+
)
8
+
9
+
func TestSlugContainsExplicitSlur(t *testing.T) {
10
+
assert := assert.New(t)
11
+
12
+
fixtures := []struct {
13
+
text string
14
+
out string
15
+
}{
16
+
{out: "", text: ""},
17
+
{out: "", text: "hello"},
18
+
{out: "chink", text: "chink"},
19
+
{out: "faggot", text: "faggot"},
20
+
{out: "faggot", text: "f4gg0t"},
21
+
{out: "coon", text: "coon"},
22
+
{out: "coon", text: "coons"},
23
+
{out: "", text: "raccoon"},
24
+
{out: "", text: "racoon"},
25
+
{out: "", text: "tycoon"},
26
+
{out: "", text: "cocoon"},
27
+
{out: "kike", text: "kike"},
28
+
{out: "nigger", text: "nigger"},
29
+
{out: "nigger", text: "niggers"},
30
+
{out: "nigger", text: "n1gg4"},
31
+
{out: "nigger", text: "niggas"},
32
+
{out: "", text: "niggle"},
33
+
{out: "", text: "niggling"},
34
+
{out: "", text: "snigger"},
35
+
{out: "tranny", text: "tranny"},
36
+
{out: "tranny", text: "trannie"},
37
+
}
38
+
39
+
for _, fix := range fixtures {
40
+
assert.Equal(fix.out, SlugContainsExplicitSlur(fix.text))
41
+
}
42
+
}
43
+
44
+
func TestStringContainsExplicitSlur(t *testing.T) {
45
+
assert := assert.New(t)
46
+
47
+
fixtures := []struct {
48
+
text string
49
+
out string
50
+
}{
51
+
{out: "", text: ""},
52
+
{out: "", text: "hello"},
53
+
{out: "chink", text: "CHINK"},
54
+
{out: "faggot", text: "f-a-g-g-o-t"},
55
+
{out: "faggot", text: "f a g g o t"},
56
+
{out: "faggot", text: "f\na\ng\ng\no\nt"},
57
+
{out: "kike", text: "kike"},
58
+
{out: "nigger", text: "niggers"},
59
+
{out: "nigger", text: "niggers.bsky.social"},
60
+
{out: "tranny", text: "trannie"},
61
+
}
62
+
63
+
for _, fix := range fixtures {
64
+
assert.Equal(fix.out, SlugContainsExplicitSlur(Slugify(fix.text)))
65
+
}
66
+
}
+49
automod/keyword/tokenize.go
+49
automod/keyword/tokenize.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"strings"
5
+
"regexp"
6
+
"unicode"
7
+
"log/slog"
8
+
9
+
"golang.org/x/text/transform"
10
+
"golang.org/x/text/unicode/norm"
11
+
"golang.org/x/text/runes"
12
+
)
13
+
14
+
var (
15
+
nonTokenChars = regexp.MustCompile(`[^\pL\pN\s]+`)
16
+
normFunc = transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC)
17
+
)
18
+
19
+
// Splits free-form text in to tokens, including lower-case, unicode normalization, and some unicode folding.
20
+
//
21
+
// The intent is for this to work similarly to an NLP tokenizer, as might be used in a fulltext search engine, and enable fast matching to a list of known tokens. It might eventually even do stemming, removing pluralization (trailing "s" for English), etc.
22
+
func TokenizeText(text string) []string {
23
+
bare := strings.ToLower(nonTokenChars.ReplaceAllString(text, ""))
24
+
norm, _, err := transform.String(normFunc, bare)
25
+
if err != nil {
26
+
slog.Warn("unicode normalization error", "err", err)
27
+
norm = bare
28
+
}
29
+
return strings.Fields(norm)
30
+
}
31
+
32
+
func splitIdentRune(c rune) bool {
33
+
return !unicode.IsLetter(c) && !unicode.IsNumber(c)
34
+
}
35
+
36
+
// Splits an identifier in to tokens. Removes any single-character tokens.
37
+
//
38
+
// For example, the-handle.bsky.social would be split in to ["the", "handle", "bsky", "social"]
39
+
func TokenizeIdentifier(orig string) []string {
40
+
fields := strings.FieldsFunc(orig, splitIdentRune)
41
+
out := make([]string, 0, len(fields))
42
+
for _, v := range fields {
43
+
tok := Slugify(v)
44
+
if len(tok) > 1 {
45
+
out = append(out, tok)
46
+
}
47
+
}
48
+
return out
49
+
}
+41
automod/keyword/tokenize_test.go
+41
automod/keyword/tokenize_test.go
···
1
+
package keyword
2
+
3
+
import (
4
+
"testing"
5
+
6
+
"github.com/stretchr/testify/assert"
7
+
)
8
+
9
+
func TestTokenizeText(t *testing.T) {
10
+
assert := assert.New(t)
11
+
12
+
fixtures := []struct {
13
+
text string
14
+
out []string
15
+
}{
16
+
{text: "", out: []string{}},
17
+
{text: "Hello, โลก!", out: []string{"hello", "โลก"}},
18
+
{text: "Gdańsk", out: []string{"gdansk"}},
19
+
}
20
+
21
+
for _, fix := range fixtures {
22
+
assert.Equal(fix.out, TokenizeText(fix.text))
23
+
}
24
+
}
25
+
26
+
func TestTokenizeIdentifier(t *testing.T) {
27
+
assert := assert.New(t)
28
+
29
+
fixtures := []struct {
30
+
ident string
31
+
out []string
32
+
}{
33
+
{ident: "", out: []string{}},
34
+
{ident: "the-handle.example.com", out: []string{"the", "handle", "example", "com"}},
35
+
{ident: "@a-b-c", out: []string{}},
36
+
}
37
+
38
+
for _, fix := range fixtures {
39
+
assert.Equal(fix.out, TokenizeIdentifier(fix.ident))
40
+
}
41
+
}