Skip to content
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

Jump to bottom

test(csv): add grapheme length test #5304

Merged
merged 4 commits into from
Jul 4, 2024
Merged

test(csv): add grapheme length test #5304

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e7cea18
initial commit
timreichen Jul 4, 2024
37fb3b5
Merge branch 'main' into csv-add-grapheme-length
timreichen Jul 4, 2024
2da1d2a
add license header
timreichen Jul 4, 2024
c2cb662
update
timreichen Jul 4, 2024
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
14 changes: 10 additions & 4 deletions csv/_io.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@
// https://github.com/golang/go/blob/master/LICENSE
// Copyright 2018-2024 the Deno authors. All rights reserved. MIT license.

import { graphemeLength } from "./_shared.ts";

/** Options for {@linkcode parseRecord}. */
export interface ReadOptions {
/** Character which separates values.
Expand Down Expand Up @@ -94,7 +96,9 @@
if (!opt.lazyQuotes) {
const j = field.indexOf(quote);
if (j >= 0) {
const col = fullLine.length + j - line.length;
const col = graphemeLength(
fullLine.slice(0, fullLine.length - line.slice(j).length),
);
throw new ParseError(startLine + 1, lineIndex, col, ERR_BARE_QUOTE);
}
}
Expand Down Expand Up @@ -132,7 +136,9 @@
recordBuffer += quote;
} else {
// `"*` sequence (invalid non-escaped quote).
const col = fullLine.length - line.length - quoteLen;
const col = graphemeLength(
fullLine.slice(0, fullLine.length - line.length - quoteLen),
);
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
} else if (line.length > 0 || !reader.isEOF()) {
Expand All @@ -145,7 +151,7 @@
if (r === null) {
// Abrupt end of file (EOF or error).
if (!opt.lazyQuotes) {
const col = fullLine.length;
const col = graphemeLength(fullLine);
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
fieldIndexes.push(recordBuffer.length);
Expand All @@ -155,7 +161,7 @@
} else {
// Abrupt end of file (EOF on error).
if (!opt.lazyQuotes) {
const col = fullLine.length;
const col = graphemeLength(fullLine);

Check warning on line 164 in csv/_io.ts

View check run for this annotation

Codecov / codecov/patch

csv/_io.ts#L164 

Added line #L164 was not covered by tests
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
fieldIndexes.push(recordBuffer.length);
Expand Down
15 changes: 15 additions & 0 deletions csv/_shared.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
// Copyright 2018-2024 the Deno authors. All rights reserved. MIT license.

/**
* returns length of a string considering surrogate pairs
* ```ts
* function graphemeLength(s: string) {
* return Array.from(s).length;
* }
* graphemeLength("🐱") // 1
* "🐱".length // 2
* ```
*/
export function graphemeLength(s: string) {
return Array.from(s).length;
}
13 changes: 9 additions & 4 deletions csv/parse.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ import {
type ReadOptions,
type RecordWithColumn,
} from "./_io.ts";
import { graphemeLength } from "./_shared.ts";

export { ParseError, type ParseResult, type RecordWithColumn };

Expand Down Expand Up @@ -108,7 +109,9 @@ class Parser {
if (!this.#options.lazyQuotes) {
const j = field.indexOf(quote);
if (j >= 0) {
const col = fullLine.length + j - line.length;
const col = graphemeLength(
fullLine.slice(0, fullLine.length - line.slice(j).length),
);
throw new ParseError(startLine + 1, lineIndex, col, ERR_BARE_QUOTE);
}
}
Expand Down Expand Up @@ -146,7 +149,9 @@ class Parser {
recordBuffer += quote;
} else {
// `"*` sequence (invalid non-escaped quote).
const col = fullLine.length - line.length - quoteLen;
const col = graphemeLength(
fullLine.slice(0, fullLine.length - line.length - quoteLen),
);
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
} else if (line.length > 0 || !(this.#isEOF())) {
Expand All @@ -159,7 +164,7 @@ class Parser {
if (r === null) {
// Abrupt end of file (EOF or error).
if (!this.#options.lazyQuotes) {
const col = fullLine.length;
const col = graphemeLength(fullLine);
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
fieldIndexes.push(recordBuffer.length);
Expand All @@ -169,7 +174,7 @@ class Parser {
} else {
// Abrupt end of file (EOF on error).
if (!this.#options.lazyQuotes) {
const col = fullLine.length;
const col = graphemeLength(fullLine);
throw new ParseError(startLine + 1, lineIndex, col, ERR_QUOTE);
}
fieldIndexes.push(recordBuffer.length);
Expand Down
11 changes: 11 additions & 0 deletions csv/parse_test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,6 +198,17 @@ Deno.test({
);
},
});
await t.step({
name: "error column grapheme number",
fn() {
const input = `a,b,🐱"`;
assertThrows(
() => parse(input),
ParseError,
'parse error on line 1, column 5: bare " in non-quoted-field',
);
},
});
await t.step({
name: "TrimQuote",
fn() {
Expand Down