Merged

Author: rijnb

CMakeLists.txt

@@ -9,6 +9,7 @@ set(SOURCE_FILES
     mapcodelib/mapcode_countrynames_short.h
     mapcodelib/mapcode_fast_encode.h
     mapcodelib/mapcode_fastalpha.h
+    mapcodelib/mapcode_territory_alphabets.h
     mapcodelib/mapcoder.c
     mapcodelib/mapcoder.h
     unittest/decode_test.h

README.md

@@ -124,11 +124,13 @@ This produces the following help text:
 * Added scripts for Korean (Choson'gul / Hangul), Burmese, Khmer, Sinhalese, Thaana (Maldivan), 
 Chinese (Zhuyin, Bopomofo), Tifinagh (Berber), Tamil, Amharic, Telugu, Odia, Kannada, Gujarati.
 
-* Renamed constants to more correct terms (Malay to Malayalam; Hindi to Devanagari). 
+* Renamed constants to more correct terms (Malay to Malayalam, Hindi to Devanagari). 
 
-* Added getAlphabetsForTerritory(t), returning the most commonly used alphabets for territory t.
+* Added `getAlphabetsForTerritory(t)`, returning the most commonly used alphabets for territory `t`.
 
-* Improved some characters for Arabic and Devanagari; Fixed Bengali to also support Assamese.
+* Improved some characters for Arabic and Devanagari.
+
+* Fixed Bengali to also support Assamese.
 
 ### 2.3.1
 

mapcodelib/mapcode_alphabets.h

@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2014-2015 Stichting Mapcode Foundation (http://www.mapcode.com)
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+#ifndef __MAPCODE_ALPHABETS_H__
+#define __MAPCODE_ALPHABETS_H__
+
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Alphabets:
+ */
+#define MAPCODE_ALPHABETS_TOTAL        28
+
+#define MAPCODE_ALPHABET_ROMAN         0
+#define MAPCODE_ALPHABET_GREEK         1
+#define MAPCODE_ALPHABET_CYRILLIC      2
+#define MAPCODE_ALPHABET_HEBREW        3
+#define MAPCODE_ALPHABET_DEVANAGARI    4
+#define MAPCODE_ALPHABET_MALAYALAM     5
+#define MAPCODE_ALPHABET_GEORGIAN      6
+#define MAPCODE_ALPHABET_KATAKANA      7
+#define MAPCODE_ALPHABET_THAI          8
+#define MAPCODE_ALPHABET_LAO           9
+#define MAPCODE_ALPHABET_ARMENIAN      10
+#define MAPCODE_ALPHABET_BENGALI       11
+#define MAPCODE_ALPHABET_GURMUKHI      12
+#define MAPCODE_ALPHABET_TIBETAN       13
+#define MAPCODE_ALPHABET_ARABIC        14
+#define MAPCODE_ALPHABET_KOREAN        15
+#define MAPCODE_ALPHABET_BURMESE       16
+#define MAPCODE_ALPHABET_KHMER         17
+#define MAPCODE_ALPHABET_SINHALESE     18
+#define MAPCODE_ALPHABET_THAANA        19
+#define MAPCODE_ALPHABET_CHINESE       20
+#define MAPCODE_ALPHABET_TIFINAGH      21
+#define MAPCODE_ALPHABET_TAMIL         22
+#define MAPCODE_ALPHABET_AMHARIC       23
+#define MAPCODE_ALPHABET_TELUGU        24
+#define MAPCODE_ALPHABET_ODIA          25
+#define MAPCODE_ALPHABET_KANNADA       26
+#define MAPCODE_ALPHABET_GUJARATI      27
+
+#define MAX_ALPHABETS_PER_TERRITORY    3
+typedef struct {
+    int count;
+    int alphabet[MAX_ALPHABETS_PER_TERRITORY];
+} TerritoryAlphabets;
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif // __MAPCODE_ALPHABETS_H__
+

mapcodelib/mapcode_countrynames.h

@@ -17,7 +17,7 @@
 #define __MAPCODE_COUNTRYNAMES_H__
 
 // *** GENERATED FILE (coords.cpp), DO NOT CHANGE OR PRETTIFY ***
-const char *isofullname[] = {
+static const char *isofullname[] = {
 "Vatican City State (Holy See)",
 "Monaco (Principality of _)",
 "Gibraltar",

mapcodelib/mapcode_countrynames_short.h

@@ -17,7 +17,7 @@
 #define __MAPCODE_COUNTRYNAMES_H__
 
 // *** GENERATED FILE (coords.cpp), DO NOT CHANGE OR PRETTIFY ***
-const char *isofullname[] = {
+static const char *isofullname[] = {
 "Vatican City State (Holy See)",
 "Monaco",
 "Gibraltar",

mapcodelib/mapcode_territory_alphabets.h

@@ -24,10 +24,9 @@ extern "C" {
 #endif
 
 #include "basics.h"
+#include "mapcode_alphabets.h"
 
-#include "mapcoder.h"
-
-TerritoryAlphabets alphabetsForTerritory[MAX_CCODE] = {
+static const TerritoryAlphabets alphabetsForTerritory[MAX_CCODE] = {
     {1, {MAPCODE_ALPHABET_ROMAN}}, // 0 VAT Vatican City State
     {1, {MAPCODE_ALPHABET_ROMAN}}, // 1 MCO Monaco
     {1, {MAPCODE_ALPHABET_ROMAN}}, // 2 GIB Gibraltar

mapcodelib/mapcoder.c

@@ -1796,7 +1796,7 @@ static struct {
                 {0x0e01, 0x0e32, "BC?D??FGHJ??O???K??L?MNP?Q?R????S?T?V?W????UXYZAIE"}, // Thai
                 {0x0e81, 0x0ec6, "BC?D??FG?H??J??????K??L?MN?P?Q??RST???V??WX?Y?ZA????????????U?????EI?O"}, // Lao
                 {0x0532, 0x0556, "BCDE??FGHI?J?KLM?N?U?PQ?R??STVWXYZ?OA"}, // Armenian
-                {0x0995, 0x09b9, "CDFBGH?AJOUKLMNPQR?S?TIVWEX??Y??????Z" }, // Bengali/Assamese
+                {0x0995, 0x09b9, "CDFBGH?AJOUKLMNPQR?S?TIVWEX??Y??????Z"}, // Bengali/Assamese
                 {0x0a05, 0x0a39, "A?????????E?????B?CD?F?G??HJZ?KL?MNP?QU?RS?T?V??W??XY"}, // Gurmukhi
                 {0x0f40, 0x0f66, "BCD?FGHJ?K?????NMP?QRLS?A?????TVUWXYE?Z"}, // Tibetan
                 {0x0627, 0x0648, "IA?BEVCDFGHJKLMNPQRS??????TU?WXYOZ"}, // Arabic
@@ -1811,20 +1811,20 @@ static struct {
                 {0x17e0, 0x17e9, ""}, // Khmer digits
                 {0x0be6, 0x0bef, ""}, // Tamil digits
                 {0x1369, 0x1372, "1234567890"}, // Amharic digits [1-9][0]
-                
+
                 {0x1100, 0x1175, "B?CD?F?G?H?OV?WXJKA??????????????????????????????????????????????????????????????????????????????LMNPQER?S???YZ???T?UI"}, // Korean
                 {0x1000, 0x101f, "BCDFGA?J????KLMYNPQESTUWX?HIZORV"}, // Burmese
                 {0x1780, 0x17a2, "BCDFGE?HJAK?LMN??PQRSTV?W?IXO??UY?Z"}, // Khmer
                 {0x0d85, 0x0dc5, "A???E?U??????????????B?C??D??F????G?H??JK?L?M?NP?Q?RSTV?W??X?IYZO"}, // Sinhalese
                 {0x0780, 0x07b1, "BCDFGHJKLMNPQRSTVWXYA?OE????U???????I????????????Z"}, // Thaana
                 {0x3105, 0x3129, "BDFCGHJKLMNRSTUEPQWYZ????I?O??A????XV"}, // Chinese                
-                {0x2d31, 0x2d63, "B?C???D????FG??H??JKL?M?A???NPI???EOQR??STVW??X?YUZ" }, // Tifinagh
-                {0x0b85, 0x0bb5, "SE?TV????WXY?ZU?B???AC???OD????F???GIH???JKLRMQPN" }, // Tamil
-                {0x1200, 0x1354, "H???????L??????????????????A??E?T?????V?????S???????????????????Q???R???????????????????????????B???C???????????W?????X????????????????????????????M????????????I???????????K???????????????????????????U???????O???????????Z???????????J???????D???????????????????????G???????????????????????????????????????????????Y?????????????????F?????N???P" }, // Amharic
-                {0x0c15, 0x0c35, "BOC?DFIG?AHJK?LMNPQR?SETUV?W?XY?Z" }, // Telugu
-                {0x0b15, 0x0b39, "BCDF?G?HA?JOKLEMNPQR?SIT?VWX??Y????ZU" }, // Odia
-                {0x0c85, 0x0cb5, "I?U?O????E???A??BCD?FGHJ???KL?MN?PQR?STVW??X?Y??Z" }, // Kannada
-                {0x0a87, 0x0ab7, "E?U???O?I?????H?B??J?CXRKNDY?L?F?W?MTGZS?P??A?Q?V" }, // Gujarati
+                {0x2d31, 0x2d63, "B?C???D????FG??H??JKL?M?A???NPI???EOQR??STVW??X?YUZ"}, // Tifinagh
+                {0x0b85, 0x0bb5, "SE?TV????WXY?ZU?B???AC???OD????F???GIH???JKLRMQPN"}, // Tamil
+                {0x1200, 0x1354, "H???????L??????????????????A??E?T?????V?????S???????????????????Q???R???????????????????????????B???C???????????W?????X????????????????????????????M????????????I???????????K???????????????????????????U???????O???????????Z???????????J???????D???????????????????????G???????????????????????????????????????????????Y?????????????????F?????N???P"}, // Amharic
+                {0x0c15, 0x0c35, "BOC?DFIG?AHJK?LMNPQR?SETUV?W?XY?Z"}, // Telugu
+                {0x0b15, 0x0b39, "BCDF?G?HA?JOKLEMNPQR?SIT?VWX??Y????ZU"}, // Odia
+                {0x0c85, 0x0cb5, "I?U?O????E???A??BCD?FGHJ???KL?MN?PQR?STVW??X?Y??Z"}, // Kannada
+                {0x0a87, 0x0ab7, "E?U???O?I?????H?B??J?CXRKNDY?L?F?W?MTGZS?P??A?Q?V"}, // Gujarati
 
                 // lowercase variants: greek, georgisch
                 {0x03AD, 0x03c9, "EU??ABGDFZHQIKLMNCOJP?STYVXRW"}, // Greek lowercase
@@ -1906,7 +1906,7 @@ static UWORD *encode_utf16(UWORD *unibuf, const int maxlen, const char *mapcode,
         if ((c < ' ') || (c > 'Z')) { // not in any valid range?
             *w++ = '?';
         } else if ((c >= '0') && (c <= '9')) { // digit?
-            *w++ = asc2lan[language][26 + (int)c - '0'];
+            *w++ = asc2lan[language][26 + (int) c - '0'];
         } else if (c < 'A') { // valid but not a letter (e.g. a dot, a space...)
             *w++ = (UWORD) c; // leave untranslated
         } else {
@@ -2555,7 +2555,7 @@ static void convertFromAbjad(char *s) {
     int len, dot, form, c;
     char *postfix = strchr(s, '-');
     dot = (int) (strchr(s, '.') - s);
-    if (dot<2 || dot>5) {
+    if (dot < 2 || dot > 5) {
         return;
     }
     if (postfix) {
@@ -2673,7 +2673,6 @@ static void convertFromAbjad(char *s) {
 }
 
 
-
 const TerritoryAlphabets *getAlphabetsForTerritory(int territoryCode) {
     const int ccode = territoryCode - 1;
     if ((ccode >= 0) && (ccode <= ccode_earth)) { // valid territory, not earth

mapcodelib/mapcoder.h

@@ -21,6 +21,9 @@
 extern "C" {
 #endif
 
+#include "mapcode_alphabets.h"
+#include "mapcode_territory_alphabets.h"
+
 #define mapcode_cversion "2.4.0"
 
 #define UWORD                               unsigned short int  // 2-byte unsigned integer.
@@ -36,6 +39,7 @@ extern "C" {
 #define MAX_CLEAN_MAPCODE_LEN               (MAX_PROPER_MAPCODE_LEN + 1 + MAX_PRECISION_DIGITS)  // Max. number of characters in a clean mapcode (excluding zero-terminator).
 #define MAX_MAPCODE_RESULT_LEN              (MAX_ISOCODE_LEN + 1 + MAX_CLEAN_MAPCODE_LEN + 1)    // Max. number of characters to store a single result (including zero-terminator).
 
+
 /**
  * The type Mapcodes hold a number of mapcodes, for example from an encoding call.
  * If a result contains a space, it splits the territory alphacode from the mapcode.
@@ -263,48 +267,6 @@ int multipleBordersNearby(
         double lon,
         int territoryCode);
 
-/**
- * Alphabets:
- */
-#define MAPCODE_ALPHABETS_TOTAL        28
-
-#define MAPCODE_ALPHABET_ROMAN         0
-#define MAPCODE_ALPHABET_GREEK         1
-#define MAPCODE_ALPHABET_CYRILLIC      2
-#define MAPCODE_ALPHABET_HEBREW        3
-#define MAPCODE_ALPHABET_DEVANAGARI    4
-#define MAPCODE_ALPHABET_MALAYALAM     5
-#define MAPCODE_ALPHABET_GEORGIAN      6
-#define MAPCODE_ALPHABET_KATAKANA      7
-#define MAPCODE_ALPHABET_THAI          8
-#define MAPCODE_ALPHABET_LAO           9
-#define MAPCODE_ALPHABET_ARMENIAN      10
-#define MAPCODE_ALPHABET_BENGALI       11
-#define MAPCODE_ALPHABET_GURMUKHI      12
-#define MAPCODE_ALPHABET_TIBETAN       13
-#define MAPCODE_ALPHABET_ARABIC        14
-#define MAPCODE_ALPHABET_KOREAN        15
-#define MAPCODE_ALPHABET_BURMESE       16
-#define MAPCODE_ALPHABET_KHMER         17
-#define MAPCODE_ALPHABET_SINHALESE     18
-#define MAPCODE_ALPHABET_THAANA        19
-#define MAPCODE_ALPHABET_CHINESE       20
-#define MAPCODE_ALPHABET_TIFINAGH      21
-#define MAPCODE_ALPHABET_TAMIL         22
-#define MAPCODE_ALPHABET_AMHARIC       23
-#define MAPCODE_ALPHABET_TELUGU        24
-#define MAPCODE_ALPHABET_ODIA          25
-#define MAPCODE_ALPHABET_KANNADA       26
-#define MAPCODE_ALPHABET_GUJARATI      27
-
-#define MAX_ALPHABETS_PER_TERRITORY 3
-typedef struct {
-  int count;
-  int alphabet[MAX_ALPHABETS_PER_TERRITORY];
-} TerritoryAlphabets;
-
-#include "mapcode_territory_alphabets.h"
-
 /**
  * Given a territory code, returns a structure defining which alphabets (in order of importance) are in common use in the territory
  *

unittest/territories.csv

@@ -1,5 +1,5 @@
 ccode,territorycodes(pipe-separated),alphabets(pipe-seperated),names(pipe-separated)
-0,VAT,0,Vatican|Holy See
+0,VAT,0,Vatican City State|Holy See
 1,MCO,0,Monaco
 2,GIB,0,Gibraltar
 3,TKL,0,Tokelau
@@ -11,7 +11,7 @@ ccode,territorycodes(pipe-separated),alphabets(pipe-seperated),names(pipe-separa
 9,SXM,0,Sint Maarten
 10,MAF,0,Saint Martin
 11,NFK|AU-NF|NF,0,Norfolk and Philip Island|Philip Island
-12,PCN,0,Pitcairn Islands
+12,PCN,0,Pitcairn Group of Islands
 13,BVT,0,Bouvet Island
 14,BMU,0,Bermuda|Somers Isles
 15,IOT|DGA,0,British Indian Ocean Territory