From 821ec273e559704ace30af1b48668113b642744c Mon Sep 17 00:00:00 2001 From: Alexis Nasr <alexis.nasr@lif.univ-mrs.fr> Date: Wed, 4 Jan 2017 22:20:30 +0100 Subject: [PATCH] added some rules in french tokenizer --- maca_tokenizer/src/fr_tok_rules.l | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/maca_tokenizer/src/fr_tok_rules.l b/maca_tokenizer/src/fr_tok_rules.l index 7e7fba8..56b0026 100644 --- a/maca_tokenizer/src/fr_tok_rules.l +++ b/maca_tokenizer/src/fr_tok_rules.l @@ -15,9 +15,13 @@ extern int defait_amalgames; [0-9]+,[0-9]* printf("%s", yytext); [ \t]+ printf("\n"); -\. printf("\n."); -\, printf("\n,"); -… printf("\n…"); +[ ]*\. printf("\n."); +[ ]*\? printf("\n?"); +[ ]*\! printf("\n!"); +[ ]*, printf("\n,"); +[ ]*: printf("\n:"); +[ ]*; printf("\n;"); +[ ]*… printf("\n…"); ' printf("'\n"); ’ printf("'\n"); -je printf("\n-je"); -- GitLab