string-array: New functions for comparing string arrays.

[pspp] / src / libpspp / i18n.h

diff --git a/src/libpspp/i18n.h b/src/libpspp/i18n.h
index a933b81b629f44d5c24c7a0803981927307acbb7..d41ef1ef2c80046f15d84404db542a038e072c5a 100644 (file)
--- a/src/libpspp/i18n.h
+++ b/src/libpspp/i18n.h
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2006, 2010, 2011 Free Software Foundation, Inc.
+   Copyright (C) 2006, 2010, 2011, 2012, 2014, 2016 Free Software Foundation, Inc.
 
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -17,6 +17,8 @@
 #ifndef I18N_H
 #define I18N_H
 
+#include "libpspp/compiler.h"
+#include "libpspp/str.h"
 #include <stdbool.h>
 #include <unistr.h>
 
@@ -40,6 +42,9 @@ char *recode_string_pool (const char *to, const char *from,
                          const char *text, int length, struct pool *);
 struct substring recode_substring_pool (const char *to, const char *from,
                                         struct substring text, struct pool *);
+int recode_pedantically (const char *to, const char *from,
+                         struct substring text, struct pool *,
+                         struct substring *out);
 
 size_t recode_string_len (const char *to, const char *from,
                           const char *text, int len);
@@ -54,6 +59,9 @@ char *utf8_encoding_concat (const char *head, const char *tail,
 size_t utf8_encoding_concat_len (const char *head, const char *tail,
                                  const char *encoding, size_t max_len);
 
+size_t utf8_count_columns (const char *, size_t);
+size_t utf8_columns_to_bytes (const char *, size_t, size_t n_columns);
+
 char *utf8_to_filename (const char *filename);
 char *filename_to_utf8 (const char *filename);
 
@@ -67,6 +75,18 @@ void set_default_encoding (const char *enc);
 bool set_encoding_from_locale (const char *loc);
 
 const char *uc_name (ucs4_t uc, char buffer[16]);
+
+unsigned int utf8_hash_case_bytes (const char *, size_t n, unsigned int basis) WARN_UNUSED_RESULT;
+unsigned int utf8_hash_case_string (const char *, unsigned int basis) WARN_UNUSED_RESULT;
+unsigned int utf8_hash_case_substring (struct substring, unsigned int basis)
+  WARN_UNUSED_RESULT;
+int utf8_strcasecmp (const char *, const char *);
+int utf8_sscasecmp (struct substring, struct substring);
+int utf8_strncasecmp (const char *, size_t, const char *, size_t);
+int utf8_strverscasecmp (const char *, const char *);
+char *utf8_to_upper (const char *);
+char *utf8_to_lower (const char *);
+char *utf8_to_title (const char *);
 \f
 /* Information about character encodings. */
 
@@ -79,7 +99,7 @@ const char *uc_name (ucs4_t uc, char buffer[16]);
        a b c d e f g h i j k l m
        n o p q r s t u v w x y z
        0 1 2 3 4 5 6 7 8 9
-       ! " # % & ' ( ) * + , - . / :
+       ! " # % & ' () * + , - . / :
        ; < = > ? [ \ ] ^ _ { | } ~
        space \a \b \r \n \t \v \f \0
 
@@ -126,13 +146,38 @@ struct encoding_info
        used in ASCII text files has the same value in this encoding. */
     bool is_ascii_compatible;
 
+    /* True if this encoding has a unit width of 1 byte and appears to be
+       EBCDIC-based.  */
+    bool is_ebcdic_compatible;
+
     /* Character information. */
     int unit;                   /* Unit width, in bytes. */
     char cr[MAX_UNIT];          /* \r in encoding, 'unit' bytes long. */
     char lf[MAX_UNIT];          /* \n in encoding, 'unit' bytes long. */
+    char space[MAX_UNIT];       /* ' ' in encoding, 'unit' bytes long. */
   };
 
 bool get_encoding_info (struct encoding_info *, const char *name);
 bool is_encoding_ascii_compatible (const char *encoding);
+bool is_encoding_ebcdic_compatible (const char *encoding);
+bool is_encoding_supported (const char *encoding);
+
+bool is_encoding_utf8 (const char *encoding);
+\f
+/* Database of encodings, by language or region. */
+
+struct encoding_category
+  {
+    const char *category;       /* e.g. "Arabic" or "Western European". */
+    const char **encodings;     /* Encodings within the category. */
+    size_t n_encodings;         /* Number of encodings in category. */
+  };
+
+struct encoding_category *get_encoding_categories (void);
+size_t get_n_encoding_categories (void);
+
+/* Return the ISO two letter code for the current LC_MESSAGES
+   locale category.  */
+char *get_language (void);
 
 #endif /* i18n.h */