fixed #13 Report utf-8-sig

Joungkyun · Jul 31, 2019 · da0a1a0 · da0a1a0
1 parent df513c4
commit da0a1a0
Show file tree

Hide file tree

Showing 25 changed files with 261 additions and 92 deletions.
diff --git a/README.md b/README.md
@@ -24,6 +24,11 @@ From 1.0.5, libchardet was reflected single-byte charset detection confidence
 algorithm of [uchardet](https://github.com/BYVoid/uchardet/) and new language models.
 (Arabic, Danish, Esperanto, German, Spanish, Turkish, Vietnamese)
 
+From 1.0.6, bom members have been added to the DetectObj structure.
+The value of the bom member is 1, which means that it has been detected as a BOM.
+Support for bom member can be determined by the existence of the CHARDET_BOM_CHECK
+constant. See example below.
+
 ## Installation
 
 See also [INSTALL](INSTALL) document
@@ -63,10 +68,18 @@ See also test directory of source code
                       return CHARDET_NULL_OBJECT;
             }
 
+        #ifndef CHARDET_BOM_CHECK
             printf ("encoding: %s, confidence: %f\n", obj->encoding, obj->confidence);
+        #else
+            // from 1.0.6 support return whether exists BOM
+            printf (
+                "encoding: %s, confidence: %f, exist BOM: %d\n",
+                 obj->encoding, obj->confidence, obj->bom
+            );
+        #endif
             detect_obj_free (&obj);
 
-           return 0;
+            return 0;
        }
 ```
 
@@ -112,7 +125,15 @@ or looping code
                           return CHARDET_NULL_OBJECT;
                 }
 
+        #ifndef CHARDET_BOM_CHECK
                 printf ("encoding: %s, confidence: %f\n", obj->encoding, obj->confidence);
+        #else
+                // from 1.0.6 support return whether exists BOM
+                printf (
+                    "encoding: %s, confidence: %f, exist BOM: %d\n",
+                    obj->encoding, obj->confidence, obj->bom
+                );
+        #endif
                 detect_obj_free (&obj);
 
                 if ( 1 )

diff --git a/man/en/detect.3 b/man/en/detect.3
@@ -1,8 +1,7 @@
-.TH detect 3 2015-12-11 "libchardet manuals"
+.TH detect 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect.3
-.\" 2016-05-05 JoungKyun.Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun.Kim <htt://oops.org>
 
 .SH NAME
 detect, detect_r \- Detecting character set and measuring accuracy of charset
@@ -113,7 +112,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# check support obj->bom with CHARDET_BOM_CHECK constant
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 
     return 0;
@@ -124,7 +124,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_handledata(3), detect_obj_init(3), detect_obj_free(3)
diff --git a/man/en/detect_destroy.3 b/man/en/detect_destroy.3
@@ -1,8 +1,7 @@
-.TH detect_destroy 3 2015-12-11 "libchardet manuals"
+.TH detect_destroy 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_destroy.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH NAME
 detect_destroy \- free Detector structure
@@ -52,7 +51,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# check support obj->bom with CHARDET_BOM_CHECK constant
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 	detect_destroy (&d);
 
@@ -64,7 +64,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_init(3), detect_reset(3)
diff --git a/man/en/detect_handledata.3 b/man/en/detect_handledata.3
@@ -1,8 +1,7 @@
-.TH detect_handledata 3 2015-12-11 "libchardet manuals"
+.TH detect_handledata 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_handledata.3
-.\" 2016-05-05 JoungKyun.Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun.Kim <htt://oops.org>
 
 .SH NAME
 detect_handledata, detect_handledata_r \- Detecting character set and measuring accuracy of charset
@@ -136,7 +135,8 @@ int main (void) {
 				return CHARDET_NULL_OBJECT;
 		}
 
-		printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+		# check support obj->bom with CHARDET_BOM_CHECK constant
+		printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 		detect_obj_free (&obj);
 	}
 	detect_destroy (&d);
@@ -149,7 +149,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_obj_init(3), detect_obj_free(3), detect_init(3), detect_reset(3), detect_destroy(3)
diff --git a/man/en/detect_init.3 b/man/en/detect_init.3
@@ -1,8 +1,7 @@
-.TH detect_init 3 2015-12-11 "libchardet manuals"
+.TH detect_init 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_init.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH NAME
 detect_init - initialize Detect structure
@@ -62,7 +61,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# check support obj->bom with CHARDET_BOM_CHECK constant
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 	detect_destroy (&d);
 
@@ -74,7 +74,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_obj_init(3), detect_obj_free(3), detect_reset(3), detect_handledata(3), detect_destroy(3)

diff --git a/man/en/detect_obj_free.3 b/man/en/detect_obj_free.3
@@ -1,8 +1,7 @@
-.TH detect_obj_free 3 2015-12-11 "libchardet manuals"
+.TH detect_obj_free 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_obj_free.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH NAME
 chardet_obj_free - free DetectObject structure
@@ -45,7 +44,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# check support obj->bom with CHARDET_BOM_CHECK constant
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 
     return 0;
@@ -56,7 +56,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_obj_init(3)

diff --git a/man/en/detect_obj_init.3 b/man/en/detect_obj_init.3
@@ -1,8 +1,7 @@
-.TH detect_obj_init 3 2015-12-11 "libchardet manuals"
+.TH detect_obj_init 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_obj_init.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH NAME
 detect_obj_init - initialize DetectObject structure
@@ -28,6 +27,7 @@ api.
 	typedef struct DetectObject {
 		char * encoding;
 		float confidence;
+		short bom;
 	} DetectObj;
 .PP
 
@@ -55,7 +55,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# check support obj->bom with CHARDET_BOM_CHECK constant
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 
     return 0;
@@ -66,7 +67,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_obj_free(3), detect(3), detect_handledata(3)

diff --git a/man/en/detect_reset.3 b/man/en/detect_reset.3
@@ -1,8 +1,7 @@
-.TH detect_reset 3 2015-12-11 "libchardet manuals"
+.TH detect_reset 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_reset.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH NAME
 detect_reset - reset Detect structure
@@ -59,7 +58,8 @@ int main (void) {
 				return CHARDET_NULL_OBJECT;
 		}
 
-		printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+		# check support obj->bom with CHARDET_BOM_CHECK constant
+		printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 		detect_obj_free (&obj);
 	}
 	detect_destroy (&d);
@@ -72,7 +72,7 @@ int main (void) {
 JoungKyun.Kim <http://oops.org>
 
 .SH "BUG REPORTS"
-Use QnA board on http://oops.org
+Use QnA board on https://github.com/Joungkyun/libchardet/issues
 
 .SH "SEE ALSO"
 detect_obj_init(3), detect_obj_free(3), detect_init(3), detect_handledata(3), detect_destroy(3)

diff --git a/man/ko/detect.3 b/man/ko/detect.3
@@ -1,8 +1,7 @@
-.TH detect 3 2016-05-05 "libchardet manuals"
+.TH detect 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect.3
-.\" 2016-05-05 JoungKyun.Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun.Kim <htt://oops.org>
 
 .SH 이름
 detect, detect_r \- 문자열의 문자셋과 정확도를 측정
@@ -46,6 +45,7 @@ API를 이용하십시오.
 	typedef struct DetectObject {
 		char * encoding;
 		float confidence;
+		short bom;
 	} DetectObj;
 .fi
 
@@ -109,7 +109,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# obj-bom 은 CHARDET_BOM_CHECK 상수 지원여부로 지원을 판단할 수 있습니다.
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 
     return 0;
@@ -120,7 +121,7 @@ int main (void) {
 김정균
 
 .SH 버그 리포트
-<http://oops.org> 의 QnA 게시판을 이용한다.
+https://github.com/Joungkyun/libchardet/issues
 
 .SH "참고"
 detect_handledata(3), detect_obj_init(3), detect_obj_free(3)
diff --git a/man/ko/detect_destroy.3 b/man/ko/detect_destroy.3
@@ -1,8 +1,7 @@
-.TH detect_destroy 3 2015-12-11 "libchardet manuals"
+.TH detect_destroy 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_destroy.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH 이름
 detect_destroy \- chardet resource를 해제한다.
@@ -51,7 +50,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# obj-bom 은 CHARDET_BOM_CHECK 상수 지원여부로 지원을 판단할 수 있습니다.
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 	detect_destroy (&d);
 
@@ -63,7 +63,7 @@ int main (void) {
 김정균
 
 .SH 버그 리포트
-<http://oops.org> 의 QnA 게시판을 이용한다.
+https://github.com/Joungkyun/libchardet/issues
 
 .SH "참고"
 detect_init(3), detect_reset(3)

diff --git a/man/ko/detect_handledata.3 b/man/ko/detect_handledata.3
@@ -1,8 +1,7 @@
-.TH detect_handledata 3 2016-05-05 "libchardet manuals"
+.TH detect_handledata 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_handledata.3
-.\" 2016-05-05 JoungKyun.Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun.Kim <htt://oops.org>
 
 .SH 이름
 detect_handledata, detect_handledata_r \- 문자셋과 정확도를 측정
@@ -131,7 +130,8 @@ int main (void) {
 				return CHARDET_NULL_OBJECT;
 		}
 
-		printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+		# obj-bom 은 CHARDET_BOM_CHECK 상수 지원여부로 지원을 판단할 수 있습니다.
+		printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 		detect_obj_free (&obj);
 	}
 	detect_destroy (&d);
@@ -144,7 +144,7 @@ int main (void) {
 김정균
 
 .SH 버그 리포트
-<http://oops.org> 의 QnA 게시판을 이용한다.
+https://github.com/Joungkyun/libchardet/issues
 
 .SH "참고"
 detect_obj_init(3), detect_obj_free(3), detect_init(3), detect_reset(3), detect_destroy(3)
diff --git a/man/ko/detect_init.3 b/man/ko/detect_init.3
@@ -1,8 +1,7 @@
-.TH detect_init 3 2015-12-11 "libchardet manuals"
+.TH detect_init 3 2019-08-01 "libchardet manuals"
 .\" Process with
 .\" nroff -man detect_init.3
-.\" 2015-12-11 JoungKyun Kim <htt://oops.org>
-.\" $Id$
+.\" 2019-08-01 JoungKyun Kim <htt://oops.org>
 
 .SH 이름
 detect_init - chardet file handle 초기화
@@ -52,7 +51,8 @@ int main (void) {
 			return CHARDET_NULL_OBJECT;
 	}
 
-	printf ("encoding: %s, confidence: %f\\n", obj->encoding, obj->confidence);
+	# obj-bom 은 CHARDET_BOM_CHECK 상수 지원여부로 지원을 판단할 수 있습니다.
+	printf ("encoding: %s, confidence: %f, exists bom: %d\\n", obj->encoding, obj->confidence, obj->bom);
 	detect_obj_free (&obj);
 	detect_destroy (&d);
 
@@ -62,9 +62,9 @@ int main (void) {
 .SH 저자
 김정균
 .SH 버그 리포트
-<http://oops.org> 의 QnA 게시판을 이용한다.
+https://github.com/Joungkyun/libchardet/issues
 .SH 저작권
-Copyright (c) 2017 JoungKyun.Kim
+Copyright (c) 2019 JoungKyun.Kim
 
 이 프로그램은 MPL/GPL2/LGPL2.1 을 따르며, 사용시의 어떠한 문제에 대하여 보증하지 않는다.
 .SH "참고"