PR/418: joveler: improve HWP detections.

3 files changed, 21 insertions, 6 deletions

diff --git a/magic/Magdir/archive b/magic/Magdir/archive
index 6d89aea4..0476ce44 100644
--- a/magic/Magdir/archive
+++ b/magic/Magdir/archive
@@ -1,5 +1,5 @@
 #------------------------------------------------------------------------------
-# $File: archive,v 1.184 2023/01/18 16:12:38 christos Exp $
+# $File: archive,v 1.185 2023/01/24 20:13:40 christos Exp $
 # archive:  file(1) magic for archive formats (see also "msdos" for self-
 #           extracting compressed archives)
 #
@@ -1774,6 +1774,16 @@
 >>50	string	epub+zip	EPUB document
 !:mime application/epub+zip
 
+# From: Hajin Jang <jb6804@naver.com>
+# hwpx (OWPML) document format follows OCF specification.
+# Hangul Word Processor 2010+ supports HWPX format.
+# URL: https://www.hancom.com/etc/hwpDownload.do
+#      https://standard.go.kr/KSCI/standardIntro/getStandardSearchView.do?menuId=503&topMenuId=502&ksNo=KSX6101
+#      https://e-ks.kr/streamdocs/view/sd;streamdocsId=72059197557727331
+>>50	string	hwp+zip     Hancom HWP (Hangul Word Processor) file, HWPX
+!:mime application/hwp+zip
+!:ext	hwpx
+
 # From:	Joerg Jenderek
 # URL:	http://en.wikipedia.org/wiki/CorelDRAW
 # NOTE:	version; til 2 WL-based; from 3 til 13 by ./riff; from 14 zip based
diff --git a/magic/Magdir/ole2compounddocs b/magic/Magdir/ole2compounddocs
index 67e7a893..99b738d9 100644
--- a/magic/Magdir/ole2compounddocs
+++ b/magic/Magdir/ole2compounddocs
@@ -1,6 +1,6 @@
 
 #------------------------------------------------------------------------------
-# $File: ole2compounddocs,v 1.23 2022/12/29 15:47:00 christos Exp $
+# $File: ole2compounddocs,v 1.24 2023/01/24 20:13:40 christos Exp $
 # Microsoft OLE 2 Compound Documents : file(1) magic for Microsoft Structured
 # storage (https://en.wikipedia.org/wiki/Compound_File_Binary_Format)
 # Additional tests for OLE 2 Compound Documents should be under this recipe.
@@ -262,9 +262,11 @@
 !:ext	tpl
 #
 # URL:	https://en.wikipedia.org/wiki/Hangul_(word_processor)
+#       https://www.hancom.com/etc/hwpDownload.do
 # Note:	"HWP Document File" signature found in FileHeader
+# Hangul Word Processor WORDIAN, 2002 and later is using HWP 5.0 format.
 # Second directory entry name FileHeader hint for Thinkfree Office document
->>>>128 	lestring16	FileHeader		: Hangul (Korean) 5.0 Word Processor File
+>>>>128 	lestring16	FileHeader		: Hancom HWP (Hangul Word Processor) file, version 5.0
 #!:mime	application/haansofthwp
 !:mime	application/x-hwp
 # https://example-files.online-convert.com/document/hwp/example.hwp
diff --git a/magic/Magdir/wordprocessors b/magic/Magdir/wordprocessors
index 22b5bba2..3a2e1cea 100644
--- a/magic/Magdir/wordprocessors
+++ b/magic/Magdir/wordprocessors
@@ -1,6 +1,6 @@
 
 #------------------------------------------------------------------------------
-# $File: wordprocessors,v 1.33 2022/12/31 20:27:17 christos Exp $
+# $File: wordprocessors,v 1.34 2023/01/24 20:13:40 christos Exp $
 # wordprocessors:  file(1) magic fo word processors.
 #
 ####### PWP file format used on Smith Corona Personal Word Processors:
@@ -442,8 +442,11 @@
 # minor version of WP file like: 0 1
 >11	byte	x	\b%d
 
-# Hangul (Korean) Word Processor File
-0	string	HWP\ Document\ File	Hangul (Korean) Word Processor File 3.0
+# Hancom HWP (Hangul Word Processor)
+# Hangul Word Processor 3.0 through 97 used HWP 3.0 format.
+# URL: https://www.hancom.com/etc/hwpDownload.do
+0	string	HWP\ Document\ File     Hancom HWP (Hangul Word Processor) file, version 3.0
+!:ext	hwp
 
 # CosmicBook, from Benoit Rouits
 0       string  CSBK    Ted Neslson's CosmicBook hypertext file