Skip to content

Handle unusual names #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
compwright wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Handle unusual names #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8a25c2a
Handle “Macayla” and “Le”
compwright Sep 19, 2018
15225e2
Fix whitespace stripping when title abbreviation is missing a period
compwright Sep 20, 2018
1aea6a2
Handle two-letter names with `y` correctly
compwright Sep 20, 2018
a50247f
Tolerate missing whitespace before suffix
compwright Sep 20, 2018
5c2b356
Handle names separated by `/`
compwright Sep 20, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 17 additions & 13 deletions namecase.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,9 @@
{ s : /\'/, r : "'"},
{ s : /\"/, r : '"'},
{ s : /\(/, r : "("},
{ s : /\./, r : "."}
{ s : /\./, r : "."},
{ s : /,/, r : ","},
{ s : /\//, r : "/"}
];

for (var i = 0; i < splitters.length; i++) {
Expand Down Expand Up @@ -96,7 +98,8 @@
.replace(/\bMacKey\b/, "Mackey")
.replace(/\bMacKley\b/, "Mackley")
.replace(/\bMacHell\b/, "Machell")
.replace(/\bMacHon\b/, "Machon");
.replace(/\bMacHon\b/, "Machon")
.replace(/\bMacAyla\b/, "Macayla");
}


Expand All @@ -107,16 +110,17 @@


// Fixes for "son (daughter) of" etc. in various languages.
.replace(/\bAl(?=\s+\w)/g, "al") // al Arabic or forename Al.
.replace(/\bAl(?=\s+\w)\b/g, "al") // al Arabic or forename Al.
.replace(/\bAp\b/g, "ap") // ap Welsh.
.replace(/\bBen(?=\s+\w)\b/g, "ben") // ben Hebrew or forename Ben.
.replace(/\bDell([ae])\b/g, "dell$1") // della and delle Italian.
.replace(/\bD([aeiu])\b/g, "d$1") // da, de, di Italian; du French.
.replace(/\bDe([lr])\b/g, "de$1") // del Italian; der Dutch/Flemish.
.replace(/\bEl\b/g, "el") // el Greek
.replace(/\bLa\b/g, "la") // la French
.replace(/\bL([eo])\b/g, "l$1") // lo Italian; le French.
.replace(/\bVan(?=\s+\w)/g, "van") // van German or forename Van.
.replace(/\bLe(?=\s+\w)\b/g, "le") // le French
.replace(/\bLo\b/g, "lo") // lo Italian
.replace(/\bVan(?=\s+\w)\b/g, "van") // van German or forename Van.
.replace(/\bVon\b/g, "von") // von Dutch/Flemish


Expand All @@ -134,14 +138,14 @@
// Somewhat arbitrary rule where two letter combos not containing vowels should be capitalized
// fixes /JJ Abrams/ and /JD Salinger/
// With some exceptions
.replace(/\b[bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ]{2}\s/, function (v) { return v.toUpperCase(); } )
.replace(/\bMR\s/, "Mr")
.replace(/\bMS\s/, "Ms")
.replace(/\bDR\s/, "Dr")
.replace(/\bST\s/, "St")
.replace(/\bJR\s/, "Jr")
.replace(/\bSR\s/, "Sr")
.replace(/\bLT\s/, "Lt")
.replace(/\b[bcdfghjklmnpqrstvwxzBCDFGHJKLMNPQRSTVWXZ]{2}\s/, function (v) { return v.toUpperCase(); } )
.replace(/\bMR\.?\b/, "Mr")
.replace(/\bMS\.?\b/, "Ms")
.replace(/\bDR\.?\b/, "Dr")
.replace(/\bST\.?\b/, "St")
.replace(/\bJR\.?\b/, "Jr")
.replace(/\bSR\.?\b/, "Sr")
.replace(/\bLT\.?\b/, "Lt")


// lowercase words
Expand Down
7 changes: 6 additions & 1 deletion test/tests.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,7 @@ var individualFields = [
"Macquarie", "Machado", "Macevicius",
"Maciulis", "Macias", "MacMurdo",
"Mackrell", "Maclin", "McConnachie",
"Macayla",
// Roman numerals
"Henry VIII", "Louis III", "Louis XIV",
"Charles II"
Expand Down Expand Up @@ -160,7 +161,11 @@ var combinedFields = [
"Bruce Wilcox", "Evan Williams", "Roberta Williams", "Sophie Wilson",
"Dave Winer", "Niklaus Wirth", "Stephen Wolfram", "Don Woods",
"Steve Wozniak", "Will Wright", "Jerry Yang", "Victor Yngve",
"Jamie Zawinski", "Philip Zimmermann", "Mark Zuckerberg"
"Jamie Zawinski", "Philip Zimmermann", "Mark Zuckerberg",
/* Unusual names */
"Khiem Le", "Macayla Carrns", "Dr Carmen Balzano", "Dr. Carmen Balzano",
"Dr Robert & Ann Leitz", "Thao & Hy Nguyen", "Ty Cobb", "Eugene L. Nath,Jr.",
"Lori & Leslie Cotton/Smith", "Ron/Alejandra Brown", "Derrick/Sandra Jackson"
];

describe('NameCase on combined fields', function () {
Expand Down