mirror of
https://github.com/ralsina/tartrazine.git
synced 2024-09-20 15:31:21 +00:00
Merge pull request #198 from creachadair/indocumentado
Add documentation comments to package tokenizer.
This commit is contained in:
commit
fe18dc0830
@ -1,3 +1,6 @@
|
|||||||
|
// Package tokenizer implements file tokenization used by the enry content
|
||||||
|
// classifier. This package is an implementation detail of enry and should not
|
||||||
|
// be imported by other packages.
|
||||||
package tokenizer
|
package tokenizer
|
||||||
|
|
||||||
import (
|
import (
|
||||||
@ -8,6 +11,9 @@ import (
|
|||||||
|
|
||||||
const byteLimit = 100000
|
const byteLimit = 100000
|
||||||
|
|
||||||
|
// Tokenize returns language-agnostic lexical tokens from content. The tokens
|
||||||
|
// returned should match what the Linguist library returns. At most the first
|
||||||
|
// 100KB of content are tokenized.
|
||||||
func Tokenize(content []byte) []string {
|
func Tokenize(content []byte) []string {
|
||||||
if len(content) > byteLimit {
|
if len(content) > byteLimit {
|
||||||
content = content[:byteLimit]
|
content = content[:byteLimit]
|
||||||
|
Loading…
Reference in New Issue
Block a user