minor bump to 1.7.1

richardlehane · Mar 12, 2017 · 23a45d0 · 23a45d0
1 parent e77c6d4
commit 23a45d0
Show file tree

Hide file tree

Showing 89 changed files with 3,871 additions and 1,291 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,11 @@
 # Change Log
+## v1.7.1 (2017-03-12)
+### Added
+- signature updates for PRONOM, LOC and tika-mimetypes
+
+### Changed
+- `roy inspect` accepts space as well as comma-separated lists of formats e.g. `roy inspect fmt/1 fmt/2`
+
 ## v1.7.0 (2017-02-17)
 ### Added
 - log files that match particular formats with `-log fmt/1,@set2` (comma separated list of format IDs/format sets). These can be mixed with regular log options e.g. `-log unknown,fmt/1,chart`
@@ -9,7 +16,7 @@
 `roy sets -changes` creates a pronom-changes.json sets file from a PRONOM release-notes.xml file; `roy sets -list @set1,@set2` lists contents of a comma-separated list of format sets
 - `roy inspect releases` provides a summary view of a PRONOM release-notes.xml file
 
-## Changed
+### Changed
 - the `sf -` command now scans stdin e.g. `cat mypdf.pdf | sf -`. You can pass a filename in to supplement the analysis with the `-name` flag. E.g. `cat myfile.pdf | sf -name myfile.pdf -`. In previous versions of sf, the dash argument signified treating stdin as a newline separated list of filenames for scanning. Use the new `-f` flag for this e.g. `sf -f myfiles.txt` or `cat myfiles.txt | sf -f -`; change requested by [pm64](https://github.com/richardlehane/siegfried/issues/96)
 
 ### Fixed

diff --git a/README.md b/README.md
@@ -8,7 +8,7 @@
 
 ### Version
 
-1.7.0
+1.7.1
 
 [![Build Status](https://travis-ci.org/richardlehane/siegfried.png?branch=master)](https://travis-ci.org/richardlehane/siegfried) [![GoDoc](https://godoc.org/github.com/richardlehane/siegfried?status.svg)](https://godoc.org/github.com/richardlehane/siegfried) [![Go Report Card](https://goreportcard.com/badge/github.com/richardlehane/siegfried)](https://goreportcard.com/report/github.com/richardlehane/siegfried)
 
@@ -87,7 +87,14 @@ Or, for the most recent updates, you can install from this fork:
     pkg install siegfried
 
 
-## Changes 
+## Changes
+### v1.7.1 (2017-03-12)
+### Added
+- signature updates for PRONOM, LOC and tika-mimetypes
+
+### Changed
+- `roy inspect` accepts space as well as comma-separated lists of formats e.g. `roy inspect fmt/1 fmt/2`
+
 ### v1.7.0 (2017-02-17)
 ### Added
 - log files that match particular formats with `-log fmt/1,@set2` (comma separated list of format IDs/format sets). These can be mixed with regular log options e.g. `-log unknown,fmt/1,chart`

diff --git a/cmd/roy/data/archivematica.sig b/cmd/roy/data/archivematica.sig
diff --git a/cmd/roy/data/default.sig b/cmd/roy/data/default.sig
diff --git a/cmd/roy/data/fddXML.zip b/cmd/roy/data/fddXML.zip
diff --git a/cmd/roy/data/pronom-tika-loc.sig b/cmd/roy/data/pronom-tika-loc.sig
diff --git a/cmd/roy/data/tika-mimetypes.xml b/cmd/roy/data/tika-mimetypes.xml
@@ -115,6 +115,15 @@
   <mime-type type="application/davmount+xml">
     <glob pattern="*.davmount"/>
   </mime-type>
+  <mime-type type="application/x-dbf">
+    <magic priority="100">
+      <match value="(?s)^[\\x02\\x03\\x30\\x31\\x32\\x43\\x63\\x83\\x8B\\xCB\\xF5\\xE5\\xFB].[\\x01-\\x0C][\\x01-\\x1F].{4}(?:.[^\\x00]|[\\x41-\\xFF].)(?:[^\\x00\\x01].|.[^\\x00]).{31}(?&lt;=[\\x00][^\\x00]{0,10})[A-Z@+]" type="regex" offset="0"/>
+    </magic>
+    <glob pattern="*.dbf"/>
+    <glob pattern="*.dbase"/>
+    <glob pattern="*.dbase3"/>
+  </mime-type>
+
   <mime-type type="application/dca-rft"/>
   <mime-type type="application/dec-dx"/>
   <mime-type type="application/dialog-info+xml"/>
@@ -356,9 +365,22 @@
   <mime-type type="application/mbms-register+xml"/>
   <mime-type type="application/mbms-register-response+xml"/>
   <mime-type type="application/mbms-user-service-description+xml"/>
+
   <mime-type type="application/mbox">
-    <sub-class-of type="text/plain"/>
+    <!-- MBOX files start with "From [sender] [date]" -->
+    <!-- To avoid false matches, check for other headers after that -->
+    <magic priority="70">
+      <match value="From " type="string" offset="0">
+         <match value="\nFrom: " type="string" offset="32:256"/>
+         <match value="\nDate: " type="string" offset="32:256"/>
+         <match value="\nDelivered-To: " type="string" offset="32:256"/>
+         <match value="\nReceived: by " type="string" offset="32:256"/>
+         <match value="\nReceived: via " type="string" offset="32:256"/>
+         <match value="\nReceived: from " type="string" offset="32:256"/>
+      </match>
+    </magic>
     <glob pattern="*.mbox"/>
+    <sub-class-of type="text/x-tika-text-based-message"/>
   </mime-type>
   <mime-type type="application/media_control+xml"/>
   <mime-type type="application/mediaservercontrol+xml">
@@ -609,6 +631,21 @@
   <mime-type type="application/prs.plucker"/>
   <mime-type type="application/qsig"/>
 
+  <mime-type type="application/vnd.ms-spreadsheetml">
+    <root-XML localName="Workbook" namespaceURI="urn:schemas-microsoft-com:office:spreadsheet"/>
+    <root-XML localName="Workbook"/>
+    <sub-class-of type="application/xml"/>
+    <_comment>Excel 2003 xml format, pre-ooxml</_comment>
+    <_comment>glob pattern typically *.xls</_comment>
+  </mime-type>
+  <mime-type type="application/vnd.ms-wordml">
+    <root-XML localName="wordDocument" namespaceURI="http://schemas.microsoft.com/office/word/2003/wordml"/>
+    <root-XML localName="wordDocument"/>
+    <sub-class-of type="application/xml"/>
+    <_comment>Word 2003 xml format, pre-ooxml</_comment>
+    <_comment>glob pattern typically *.doc</_comment>
+  </mime-type>
+
   <mime-type type="application/rdf+xml">
     <root-XML localName="RDF"/>
     <root-XML localName="RDF" namespaceURI="http://www.w3.org/1999/02/22-rdf-syntax-ns#"/>
@@ -3089,6 +3126,18 @@
     <sub-class-of type="text/x-tika-text-based-message"/>
   </mime-type>
 
+  <mime-type type="application/x-endnote-refer">
+    <magic priority="80">
+      <match value="%A " type="string" offset="0:50">
+        <match value="\n%D " type="string" offset="0:1000">
+          <match value="\n%T " type="string" offset="0:1000"/>
+        </match>
+      </match>
+    </magic>
+    <glob pattern="*.enw"/>
+    <glob pattern="*.enr"/>
+  </mime-type>
+
   <mime-type type="application/x-killustrator">
     <_comment>KIllustrator File</_comment>
     <glob pattern="*.kil"/>
@@ -3444,6 +3493,13 @@
   <mime-type type="application/x-ms-application">
     <glob pattern="*.application"/>
   </mime-type>
+  <mime-type type="application/x-ms-owner">
+    <_comment>Temporary files created by MSOffice applications</_comment>
+    <_comment>PRONOM fmt-473</_comment>
+    <magic priority="80">
+      <match value="(?s)^([\\x05-\\x0F]).{53}\\1\x00" type="regex" offset="0"/>
+    </magic>
+  </mime-type>
   <mime-type type="application/x-ms-wmd">
     <glob pattern="*.wmd"/>
   </mime-type>
@@ -3848,6 +3904,58 @@
     </magic>
   </mime-type>
 
+  <mime-type type="application/x-stata-do">
+    <_comment>Stata DTA Script</_comment>
+    <acronym>DO</acronym>
+    <tika:link>http://www.stata.com/help.cgi?do</tika:link>
+    <glob pattern="*.do"/>
+  </mime-type>
+
+  <mime-type type="application/x-stata-dta">
+    <_comment>Stata DTA Dataset</_comment>
+    <acronym>DTA</acronym>
+    <tika:link>http://www.stata.com/help.cgi?dta</tika:link>
+	 <root-XML localName="stata_dta"/>
+    <magic priority="50">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>" type="string" offset="0"/>
+    </magic>
+    <magic priority="40">
+      <match value="&lt;stata_dta>" type="string" offset="0"/>
+    </magic>
+    <glob pattern="*.dta"/>
+  </mime-type>
+
+  <mime-type type="application/x-stata-dta;version=14">
+    <sub-class-of type="application/x-stata-dta"/>
+    <magic priority="60">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>118&lt;/release>" type="string" offset="0"/>
+    </magic>
+  </mime-type>
+  <mime-type type="application/x-stata-dta;version=13">
+    <sub-class-of type="application/x-stata-dta"/>
+    <magic priority="60">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>117&lt;/release>" type="string" offset="0"/>
+    </magic>
+  </mime-type>
+  <mime-type type="application/x-stata-dta;version=12">
+    <sub-class-of type="application/x-stata-dta"/>
+    <magic priority="60">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>115&lt;/release>" type="string" offset="0"/>
+    </magic>
+  </mime-type>
+  <mime-type type="application/x-stata-dta;version=10">
+    <sub-class-of type="application/x-stata-dta"/>
+    <magic priority="60">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>114&lt;/release>" type="string" offset="0"/>
+    </magic>
+  </mime-type>
+  <mime-type type="application/x-stata-dta;version=8">
+    <sub-class-of type="application/x-stata-dta"/>
+    <magic priority="60">
+      <match value="&lt;stata_dta>&lt;header>&lt;release>113&lt;/release>" type="string" offset="0"/>
+    </magic>
+  </mime-type>
+
   <mime-type type="application/x-stuffit">
     <magic priority="50">
       <match value="StuffIt" type="string" offset="0"/>
@@ -3946,10 +4054,11 @@
   <!-- =================================================================== -->
   <mime-type type="application/x-tika-ooxml">
     <sub-class-of type="application/zip"/>
-    <!-- Only works if the Content Types file is the first zip entry -->
+    <!-- Only works if the Content Types or rels file is the first zip entry -->
     <magic priority="50">
       <match value="PK\003\004" type="string" offset="0">
         <match value="[Content_Types].xml" type="string" offset="30"/>
+        <match value="_rels/.rels" type="string" offset="30"/>
       </match>
     </magic>
   </mime-type>
@@ -4865,6 +4974,9 @@
   <mime-type type="image/vnd.djvu">
     <glob pattern="*.djvu"/>
     <glob pattern="*.djv"/>
+    <magic priority="50">
+      <match value="AT&amp;TFORM" type="string" offset="0"/>
+    </magic>
   </mime-type>
 
   <mime-type type="image/vnd.dwg">
@@ -5284,6 +5396,7 @@
 
   <mime-type type="message/rfc822">
     <magic priority="50">
+      <match value="Delivered-To:" type="string" offset="0"/>
       <match value="Status:" type="string" offset="0"/>
       <match value="X-Mozilla-Status:" type="string" offset="0"/>
       <match value="X-Mozilla-Status2:" type="string" offset="0"/>
@@ -5469,8 +5582,14 @@
   </mime-type>
 
   <mime-type type="text/calendar">
+    <magic priority="50">
+      <match value="BEGIN:VCALENDAR" type="string" offset="0">
+        <match value="VERSION:2.0" type="string" offset="15:30"/>
+      </match>
+    </magic>
     <glob pattern="*.ics"/>
     <glob pattern="*.ifb"/>
+    <sub-class-of type="text/plain"/>
   </mime-type>
 
   <mime-type type="text/css">
@@ -6225,6 +6344,11 @@
   </mime-type>
 
   <mime-type type="text/x-vcalendar">
+    <magic priority="50">
+      <match value="BEGIN:VCALENDAR" type="string" offset="0">
+        <match value="VERSION:1.0" type="string" offset="15:30"/>
+      </match>
+    </magic>
     <glob pattern="*.vcs"/>
     <sub-class-of type="text/plain"/>
   </mime-type>
@@ -6548,11 +6672,17 @@
 
   <mime-type type="video/x-ms-asf">
     <glob pattern="*.asf"/>
-    <glob pattern="*.asx"/>
     <magic>
        <match value="0x3026b275" type="big32" offset="0" />
     </magic>
   </mime-type>
+  <mime-type type="application/x-ms-asx">
+    <_comment>Windows Media Metafile</_comment>
+    <glob pattern="*.asx"/>
+    <root-XML localName="asx"/>
+    <root-XML localName="ASX"/>
+    <sub-class-of type="application/xml"/>
+  </mime-type>
   <mime-type type="video/x-ms-wm">
     <glob pattern="*.wm"/>
   </mime-type>

diff --git a/glide.lock b/glide.lock
diff --git a/pkg/config/siegfried.go b/pkg/config/siegfried.go
@@ -43,7 +43,7 @@ var siegfried = struct {
 	out        io.Writer
 	checkpoint int64
 }{
-	version:         [3]int{1, 7, 0},
+	version:         [3]int{1, 7, 1},
 	signature:       "default.sig",
 	magic:           []byte{'s', 'f', 0x00, 0xFF},
 	distance:        8192,

diff --git a/pkg/loc/loc.go b/pkg/loc/loc.go
@@ -47,7 +47,7 @@ func newLOC(path string) (identifier.Parseable, error) {
 	fs := make([]mappings.FDD, 0, len(rc.File))
 	for _, f := range rc.File {
 		dir, nm := filepath.Split(f.Name)
-		if dir == "fddXML/" && nm != "" && filepath.Ext(nm) == ".xml" {
+		if dir == "fddXML/" && nm != "" && filepath.Ext(nm) == ".xml" && !strings.Contains(nm, "test") {
 			res := mappings.FDD{}
 			rdr, err := f.Open()
 			if err != nil {

diff --git a/vendor/golang.org/x/image/draw/go1_8.go b/vendor/golang.org/x/image/draw/go1_8.go
diff --git a/vendor/golang.org/x/image/draw/go1_9.go b/vendor/golang.org/x/image/draw/go1_9.go