From 4bfa775728a1ce883006aefbf2b857e211bd5f35 Mon Sep 17 00:00:00 2001 From: Olivier Duval Date: Tue, 22 Oct 2024 09:45:39 +0200 Subject: [PATCH] Changed Charset in InputStream --- README.md | 4 ++++ src/main/java/fr/doap/dicofr/POSTagger.java | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) create mode 100644 README.md diff --git a/README.md b/README.md new file mode 100644 index 0000000..2638fa2 --- /dev/null +++ b/README.md @@ -0,0 +1,4 @@ +# Dico-FR + +Une application de dictionnaire simple pour attribuer les POS d'un texte en français. + diff --git a/src/main/java/fr/doap/dicofr/POSTagger.java b/src/main/java/fr/doap/dicofr/POSTagger.java index 10505bf..fceba9c 100644 --- a/src/main/java/fr/doap/dicofr/POSTagger.java +++ b/src/main/java/fr/doap/dicofr/POSTagger.java @@ -17,7 +17,8 @@ public class POSTagger { protected void init() { try (InputStream lIS = POSTagger.class.getResourceAsStream("/dict.txt")) { - BufferedReader lISR = new BufferedReader(new InputStreamReader(lIS, "Windows-1252")); + BufferedReader lISR = new BufferedReader(new InputStreamReader(lIS)); +// BufferedReader lISR = new BufferedReader(new InputStreamReader(lIS, "Windows-1252")); lISR.lines().forEach(aS -> { String[] lS = aS.split("\\t"); String[] lType = lS[2].split(" ");