source: other-projects/nightly-tasks/diffcol/trunk/model-collect/Multimedia/etc/collect.cfg@ 29477

Last change on this file since 29477 was 29477, checked in by ak19, 9 years ago

Second of 2 commits (previous committed as user sjs49) to get diffcol on the 64 bit Ubuntu that has perl 5.18 to work again for the Multimedia and MARC-Singlefile collections. This commit does updates the etc/collect.cfg for both collections, sets a dc.Title for a doc in the Multimedia collection (strawberry.txt in tablature, now set to Strawberry Fields For Ever, whereas it defaulted to Forever as one word) which produced a new metadata.xml inside the tablature folder, and an updated marc file for the MARC-Singlefile collection, which has 2 changes: a duplicate subject of Computer Programming was removed from a Steve Reeves paper and the subject Database management occurred frequently with a period at end and once without period, the last of which has now got a period too for merging with the other. The collect.cfg file for Multimedia sorts the AZCompactList classifier by ex.Identifier and sets the removeprefix flag to ignore occurrences of A and The at the start of titles, and modifies the removesuffix flag to not require a space between the final character of a title and any subsequent punctuation. All these changes were necessary to ensure that the ordering (of titles and other influential metadata) was always consistent by making them unique, by making more titles group into bookshelves, or enforcing a sort order.

File size: 2.6 KB
RevLine 
[28038]1creator
2maintainer
3public true
4
5buildtype mgpp
6infodbtype gdbm
7
8indexes text dc.Title,ex.dc.Title,ex.Title ex.Source
9defaultindex text
10
11levels document
12
[28237]13indexoptions accentfold casefold stem
14
15defaultlevel document
16
[28038]17# import options, needed for diffcol testing
18# especially in conjunction with -sort flag to ArchivesInfPlugin
19OIDtype hash_on_full_filename
20sortmeta OID
21
22plugin ZIPPlugin
23plugin GreenstoneXMLPlugin
24plugin TextPlugin
25plugin HTMLPlugin
26plugin EmailPlugin
27plugin PDFPlugin
28plugin RTFPlugin
29plugin WordPlugin
30plugin PostScriptPlugin
31plugin PowerPointPlugin
32plugin ExcelPlugin
33plugin ImagePlugin
34plugin ISISPlugin
35plugin NulPlugin
36plugin EmbeddedMetadataPlugin
37plugin MP3Plugin
38plugin MARCPlugin
39plugin UnknownPlugin -mime_type audio/midi -process_extension mid -file_format MIDI
40plugin MetadataXMLPlugin
41plugin ArchivesInfPlugin -sort
42plugin DirectoryPlugin
43
[29477]44classify AZCompactList -metadata dc.Title,ex.Title -removesuffix (?i)(\\s+\\d+)|(\\s*[[:punct:]].*) -removeprefix (?i)(a|the)\\s* -sort ex.Identifier
[28038]45classify List -sort_leaf_nodes_using ex.Title -metadata dc.Format -buttonname browse -partition_type_within_level none -bookshelf_type always
46
47format VList "<td valign=top>
48{If}{[numleafdocs],[link][icon][/link]}
49{If}{[dc.Format] eq \'Lyrics\',[link]_iconlyrics_[/link]}
50{If}{[dc.Format] eq \'Discography\',[link]_icondisc_[/link]}
51{If}{[dc.Format] eq \'Tablature\',[link]_icontab_[/link]}
52{If}{[dc.Format] eq \'MARC\',[link]_iconmarc_[/link]}
53{If}{[dc.Format] eq \'Images\',[srclink][thumbicon][/srclink]}
54{If}{[dc.Format] eq \'Supplementary\',[srclink][srcicon][/srclink]}
55{If}{[dc.Format] eq \'Audio\',[srclink]{If}{[FileFormat] eq \'MIDI\',_iconmidi_,_iconmp3_}[/srclink]}
56</td>
57<td>
58{If}{[numleafdocs],([numleafdocs])}
59</td>
60<td valign=top>
61[highlight]
62{Or}{[dc.Title],[Title],Untitled}
63[/highlight]
64</td>"
65
66format HList "[link][highlight][ex.Title][/highlight][/link]"
67
68format DocumentHeading "{Or}{[parent(Top):Title],[Title],untitled}<br>"
69
70format DocumentText "[Text]"
71
72format DocumentButtons "Detach|Highlight"
73
74format SearchTypes "plain,form"
75
76collectionmeta collectionname [l=en] "Multimedia"
77collectionmeta .text [l=en] "_labeltext_"
78collectionmeta .dc.Title,ex.dc.Title,Title [l=en] "_labelTitle_"
79collectionmeta .Source [l=en] "_labelSource_"
80collectionmeta .document [l=en] "_textdocument_"
81collectionmeta .section [l=en] "_textsection_"
82collectionmeta .document:text [l=en] "_labeltext_"
83collectionmeta .document:dc.Title,Title,ex.dc.Title [l=en] "_labelTitle_"
84collectionmeta .document:Source [l=en] "_labelSource_"
85collectionmeta .document:dc.Title,Title [l=en] "_labelTitle_"
86collectionmeta iconcollection [l=en] "_httpprefix_/collect/Multimedia/images/beatlesmm.png"
Note: See TracBrowser for help on using the repository browser.