marc 0.8.1 → 0.8.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/marc/reader.rb +9 -3
- data/lib/marc/version.rb +1 -1
- data/lib/marc/writer-NEW.rb +108 -0
- data/test/bib178448.okay.human +24 -0
- data/test/bib178448.okay.marc +1 -0
- data/test/bib178448.writtenout.marc +1 -0
- data/test/hebrew880s.marc +1 -0
- data/test/marc_with_bad_utf8.utf8.human +40 -0
- metadata +30 -2
data/lib/marc/reader.rb
CHANGED
|
@@ -1,9 +1,8 @@
|
|
|
1
|
-
require '
|
|
1
|
+
require 'scrub_rb'
|
|
2
2
|
|
|
3
3
|
# Note: requiring 'marc/marc8/to_unicode' below, in #initialize,
|
|
4
4
|
# only when necessary
|
|
5
5
|
|
|
6
|
-
|
|
7
6
|
module MARC
|
|
8
7
|
# A class for reading MARC binary (ISO 2709) files.
|
|
9
8
|
#
|
|
@@ -413,7 +412,14 @@ module MARC
|
|
|
413
412
|
if params[:internal_encoding]
|
|
414
413
|
str = str.encode(params[:internal_encoding], params)
|
|
415
414
|
elsif (params[:invalid] || params[:replace] || (params[:validate_encoding] == true))
|
|
416
|
-
|
|
415
|
+
|
|
416
|
+
if params[:validate_encoding] == true && ! str.valid_encoding?
|
|
417
|
+
raise Encoding::InvalidByteSequenceError.new("invalid byte in string for source encoding #{str.encoding.name}")
|
|
418
|
+
end
|
|
419
|
+
if params[:invalid] == :replace
|
|
420
|
+
str = str.scrub(params[:replace])
|
|
421
|
+
end
|
|
422
|
+
|
|
417
423
|
end
|
|
418
424
|
end
|
|
419
425
|
return str
|
data/lib/marc/version.rb
CHANGED
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
module MARC
|
|
2
|
+
|
|
3
|
+
# A class for writing MARC records as MARC21.
|
|
4
|
+
|
|
5
|
+
class Writer
|
|
6
|
+
|
|
7
|
+
# the constructor which you must pass a file path
|
|
8
|
+
# or an object that responds to a write message
|
|
9
|
+
|
|
10
|
+
def initialize(file)
|
|
11
|
+
if file.class == String
|
|
12
|
+
@fh = File.new(file,"w")
|
|
13
|
+
elsif file.respond_to?('write')
|
|
14
|
+
@fh = file
|
|
15
|
+
else
|
|
16
|
+
throw "must pass in file name or handle"
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
# write a record to the file or handle
|
|
22
|
+
|
|
23
|
+
def write(record)
|
|
24
|
+
@fh.write(MARC::Writer.encode(record))
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
# close underlying filehandle
|
|
29
|
+
|
|
30
|
+
def close
|
|
31
|
+
@fh.close
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
# a static method that accepts a MARC::Record object
|
|
36
|
+
# and returns the record encoded as MARC21 in transmission format
|
|
37
|
+
|
|
38
|
+
def self.encode(record)
|
|
39
|
+
directory = ''
|
|
40
|
+
fields = ''
|
|
41
|
+
offset = 0
|
|
42
|
+
for field in record.fields
|
|
43
|
+
|
|
44
|
+
# encode the field
|
|
45
|
+
field_data = ''
|
|
46
|
+
if field.class == MARC::DataField
|
|
47
|
+
warn("Warn: Missing indicator") unless field.indicator1 && field.indicator2
|
|
48
|
+
field_data = (field.indicator1 || " ") + (field.indicator2 || " ")
|
|
49
|
+
for s in field.subfields
|
|
50
|
+
field_data += SUBFIELD_INDICATOR + s.code + s.value
|
|
51
|
+
end
|
|
52
|
+
elsif field.class == MARC::ControlField
|
|
53
|
+
field_data = field.value
|
|
54
|
+
end
|
|
55
|
+
field_data += END_OF_FIELD
|
|
56
|
+
|
|
57
|
+
# calculate directory entry for the field
|
|
58
|
+
field_length = (field_data.respond_to?(:bytesize) ?
|
|
59
|
+
field_data.bytesize() :
|
|
60
|
+
field_data.length())
|
|
61
|
+
directory += sprintf("%03s", field.tag) + format_byte_count(field_length, 4) + format_byte_count(offset)
|
|
62
|
+
|
|
63
|
+
|
|
64
|
+
# add field to data for other fields
|
|
65
|
+
fields += field_data
|
|
66
|
+
|
|
67
|
+
# update offset for next field
|
|
68
|
+
offset += field_length
|
|
69
|
+
end
|
|
70
|
+
|
|
71
|
+
# determine the base (leader + directory)
|
|
72
|
+
base = record.leader + directory + END_OF_FIELD
|
|
73
|
+
|
|
74
|
+
# determine complete record
|
|
75
|
+
marc = base + fields + END_OF_RECORD
|
|
76
|
+
|
|
77
|
+
# update leader with the byte offest to the end of the directory
|
|
78
|
+
marc[12..16] = format_byte_count(base.respond_to?(:bytesize) ?
|
|
79
|
+
base.bytesize() :
|
|
80
|
+
base.length()
|
|
81
|
+
)
|
|
82
|
+
|
|
83
|
+
# update the record length
|
|
84
|
+
marc[0..4] = format_byte_count(marc.respond_to?(:bytesize) ?
|
|
85
|
+
marc.bytesize() :
|
|
86
|
+
marc.length()
|
|
87
|
+
)
|
|
88
|
+
|
|
89
|
+
# store updated leader in the record that was passed in
|
|
90
|
+
record.leader = marc[0..LEADER_LENGTH-1]
|
|
91
|
+
|
|
92
|
+
# return encoded marc
|
|
93
|
+
return marc
|
|
94
|
+
end
|
|
95
|
+
|
|
96
|
+
def self.format_byte_count(number, num_digits=5)
|
|
97
|
+
formatted = sprintf("%0#{num_digits}i", number)
|
|
98
|
+
if formatted.length > num_digits
|
|
99
|
+
# uh, oh, we've exceeded our max. Either zero out
|
|
100
|
+
# or raise, depending on settings.
|
|
101
|
+
#formatted = sprintf("%0#{num_digits}i", "")
|
|
102
|
+
formatted = "9" * num_digits
|
|
103
|
+
end
|
|
104
|
+
return formatted
|
|
105
|
+
end
|
|
106
|
+
|
|
107
|
+
end
|
|
108
|
+
end
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
01161cam a2200289 4500
|
|
2
|
+
001 178448
|
|
3
|
+
008 s1996 xx spa d
|
|
4
|
+
035 $a X!b
|
|
5
|
+
049 $a JHWV [AV] [NIRC] $n o
|
|
6
|
+
096 $a WY 20.5 VC6 1996
|
|
7
|
+
110 2 $a National Institutes of Health (U.S.)
|
|
8
|
+
110 2 $a National Institute of Nursing Research (U.S.)
|
|
9
|
+
110 2 $a Department of Health & Human Services (U.S.)
|
|
10
|
+
245 0 $a Ten years at NIH : $b advancing health through science : the human dimension / $c Patricia A. Grady, Harold Varmus.
|
|
11
|
+
246 $a 10 years at NIH
|
|
12
|
+
300 $a 2 videocassettes (229 min.) : $b sd., col. ; $c 1/2 in.
|
|
13
|
+
520 $a A series of speakers recounts advances in nursing research from 1986 to 1996.
|
|
14
|
+
538 $a VHS.
|
|
15
|
+
650 2 $a Nursing Care $x videocassettes
|
|
16
|
+
650 2 $a Nursing Research $x videocassettes
|
|
17
|
+
650 2 $a Nursing $x videocassettes
|
|
18
|
+
700 10 $a Grady, Patricia Anne, $d 1943-
|
|
19
|
+
700 1 $a Varmus, Harold
|
|
20
|
+
910 $a 178448 $b Horizon bib#
|
|
21
|
+
949 31 $7 1 $5 WY 20.5 VC6 1996 $0 26 $0 G $2 A $8 5 $4 1
|
|
22
|
+
991 $a WY 20.5 VC6 1996 $f nlm $b wnlm $c c. 1 $q 0 $i 3199765 $l wempbk $m elsc
|
|
23
|
+
991 $a WY 20.5 VC6 1996 $f nlm $b wnlm $c c. 1 $q 0 $i 3199766 $l wempbk $m elsc
|
|
24
|
+
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
01161cam a2200289 4500001000700000008004100007035000800048049002400056096002100080110004100101110005100142110004900193245011600242246002000358300005600378520008500434538000900519650003300528650003700561650002800598700003300626700001900659910002500678949004000703991006400743991006400807 178448 s1996 xx spa d aX!b aJHWV [AV] [NIRC] no aWY 20.5 VC6 1996 2 aNational Institutes of Health (U.S.) 2 aNational Institute of Nursing Research (U.S.) 2 aDepartment of Health & Human Services (U.S.) 0 aTen years at NIH : badvancing health through science : the human dimension / cPatricia A. Grady, Harold Varmus. a10 years at NIH a2 videocassettes (229 min.) : bsd., col. ; c1/2 in. aA series of speakers recounts advances in nursing research from 1986 to 1996. aVHS. 2 aNursing Care xvideocassettes 2 aNursing Research xvideocassettes 2 aNursing xvideocassettes 10 aGrady, Patricia Anne, d1943- 1 aVarmus, Harold a178448 bHorizon bib# 31 71 5WY 20.5 VC6 1996 026 0G 2A 85 41 aWY 20.5 VC6 1996 fnlm bwnlm cc. 1 q0 i3199765 lwempbk melsc aWY 20.5 VC6 1996 fnlm bwnlm cc. 1 q0 i3199766 lwempbk melsc
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
01161cam a2200289 4500001000700000008004100007035000800048049002400056096002100080110004100101110005100142110004900193245011600242246002000358300005600378520008500434538000900519650003300528650003700561650002800598700003300626700001900659910002500678949004000703991006400743991006400807 178448 s1996 xx spa d aX!b aJHWV [AV] [NIRC] no aWY 20.5 VC6 1996 2 aNational Institutes of Health (U.S.) 2 aNational Institute of Nursing Research (U.S.) 2 aDepartment of Health & Human Services (U.S.) 0 aTen years at NIH : badvancing health through science : the human dimension / cPatricia A. Grady, Harold Varmus. a10 years at NIH a2 videocassettes (229 min.) : bsd., col. ; c1/2 in. aA series of speakers recounts advances in nursing research from 1986 to 1996. aVHS. 2 aNursing Care xvideocassettes 2 aNursing Research xvideocassettes 2 aNursing xvideocassettes 10 aGrady, Patricia Anne, d1943- 1 aVarmus, Harold a178448 bHorizon bib# 31 71 5WY 20.5 VC6 1996 026 0G 2A 85 41 aWY 20.5 VC6 1996 fnlm bwnlm cc. 1 q0 i3199765 lwempbk melsc aWY 20.5 VC6 1996 fnlm bwnlm cc. 1 q0 i3199766 lwempbk melsc
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
01998cam a2200469 a 4500001000800000005001700008008004100025020001800066020001500084024001800099024001200117035001200129035001700141035002100158040003200179042000800211049000900219050002100228066000700249100002900256245010000285246008400385260015000469300002100619504006400640541010900704600004100813600004700854650002500901650002300926650002900949650002500978752002201003880003701025880013001062880017301192910002601365936002701391938003801418991006001456994001201516 4083985 20120302131100.0 110313s2011 is b 001 0 heb c a9789651321337 a9651321334 8 a0003200213195 8 a3221319 a4083985 aocn710973037 a(OCoLC)710973037 aWEINB cWEINB dHLS dIXA dCUY apcc aJHEE 4 aDS149 b.R38 2011 c(2 1 6880-01 aRatsabi, Shalom. 10 6880-02 aAnarkhizm be-"Tsiyon" : bben Marṭin Buber le-Aharon Daṿid Gordon / cShalom Ratsabi. 1 iTitle on t.p. verso: aAnarchy in "Zion" : bbetween Martin Buber and A.D. Gordon 6880-03 a[Tel Aviv] : bʻAm ʻoved : bha-Makhon le-ḥeḳer ha-Tsiyonut ve-Yiśra'el ʻa. sh. Ḥayim Ṿaitsman, Universiṭat Tel Aviv, cc2011. a339 p. ; c23 cm. aIncludes bibliographical references (p. 320-330) and index. 3Eisenhower copy: cPurchased with support from the National Endowment for the Humanities; dFY2012. 5MdBJ. 10 aBuber, Martin, d1878-1965 xReligion. 10 aGordon, Aaron David, d1856-1922 xReligion. 0 aZionism and Judaism. 0 aReligious Zionism. 0 aZionism xHistoriography. 0 aZionism xPhilosophy. aIsrael dTel Aviv. 1 6100-01/(2/r aרצבי, שלום. 10 6245-02/(2/r aאנרכיזם ב״ציון״ : bבין מרטין בובר לאהרן דוד גורדון / cשלום רצבי. 6260-03/(2/r a[תל אביב] : bעם עובד : bהמכון לחקר הציונות וישראל עʺש חיים ויצמן, אוניברסיטת תל אביב, cc2011. a4083985 bHorizon bib# aPR 747581025 741225747 aA.I. Weinberg bWEIN nwb2011369996 aDS149.R38 2011 flc belc cc. 1 q0 i6085034 lemain memsel aC0 bJHE
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
01161cam a2200289 4500
|
|
2
|
+
001 178448
|
|
3
|
+
008 s1996 xx spa d
|
|
4
|
+
035 $a X!b
|
|
5
|
+
049 $a JHWV [AV] [NIRC] $n o
|
|
6
|
+
096 $a WY 20.5 VC6 1996
|
|
7
|
+
110 2 $a National Institutes of Health (U.S.)
|
|
8
|
+
110 2 $a National Institute of Nursing Research (U.S.)#
|
|
9
|
+
(No separator at end of field length=51)
|
|
10
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
11
|
+
110 2 $a Department of Health & Human Services (U.S.)
|
|
12
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
13
|
+
245 0 $a Ten years at NIH : $b advancing health through science : the human dimension / $c Patricia A. Grady, Harold Varmus.
|
|
14
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
15
|
+
246 $a 10 years at NIH
|
|
16
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
17
|
+
300 $a 2 videocassettes (229 min.) : $b sd., col. ; $c 1/2 in.
|
|
18
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
19
|
+
520 $a A series of speakers recounts advances in nursing research from 1986 to 1996.
|
|
20
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
21
|
+
538 $a VHS.
|
|
22
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
23
|
+
650 2 $a Nursing Care $x videocassettes
|
|
24
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
25
|
+
650 2 $a Nursing Research $x videocassettes
|
|
26
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
27
|
+
650 2 $a Nursing $x videocassettes
|
|
28
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
29
|
+
700 10 $a Grady, Patricia Anne, $d 1943-
|
|
30
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
31
|
+
700 1 $a Varmus, Harold
|
|
32
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
33
|
+
910 $a 178448 $b Horizon bib#
|
|
34
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
35
|
+
949 31 $7 1 $5 WY 20.5 VC6 1996 $0 26 $0 G $2 A $8 5 $4 1
|
|
36
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
37
|
+
991 $a WY 20.5 VC6 1996 $f nlm $b wnlm $c c. 1 $q 0 $i 3199765 $l wempbk $m elsc
|
|
38
|
+
(Bad indicator data. Skipping 2 bytes)
|
|
39
|
+
991 $a WY 20.5 VC6 1996 $f nlm $b wnlm $c c. 1 $q 0 $i 3199766 $l wempbk $m elsc
|
|
40
|
+
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: marc
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.8.
|
|
4
|
+
version: 0.8.2
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -14,7 +14,7 @@ authors:
|
|
|
14
14
|
autorequire: marc
|
|
15
15
|
bindir: bin
|
|
16
16
|
cert_chain: []
|
|
17
|
-
date:
|
|
17
|
+
date: 2014-09-16 00:00:00.000000000 Z
|
|
18
18
|
dependencies:
|
|
19
19
|
- !ruby/object:Gem::Dependency
|
|
20
20
|
name: ensure_valid_encoding
|
|
@@ -32,6 +32,28 @@ dependencies:
|
|
|
32
32
|
- - ! '>='
|
|
33
33
|
- !ruby/object:Gem::Version
|
|
34
34
|
version: '0'
|
|
35
|
+
- !ruby/object:Gem::Dependency
|
|
36
|
+
name: scrub_rb
|
|
37
|
+
requirement: !ruby/object:Gem::Requirement
|
|
38
|
+
none: false
|
|
39
|
+
requirements:
|
|
40
|
+
- - ! '>='
|
|
41
|
+
- !ruby/object:Gem::Version
|
|
42
|
+
version: 1.0.1
|
|
43
|
+
- - <
|
|
44
|
+
- !ruby/object:Gem::Version
|
|
45
|
+
version: '2'
|
|
46
|
+
type: :runtime
|
|
47
|
+
prerelease: false
|
|
48
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
49
|
+
none: false
|
|
50
|
+
requirements:
|
|
51
|
+
- - ! '>='
|
|
52
|
+
- !ruby/object:Gem::Version
|
|
53
|
+
version: 1.0.1
|
|
54
|
+
- - <
|
|
55
|
+
- !ruby/object:Gem::Version
|
|
56
|
+
version: '2'
|
|
35
57
|
- !ruby/object:Gem::Dependency
|
|
36
58
|
name: unf
|
|
37
59
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -65,6 +87,7 @@ files:
|
|
|
65
87
|
- lib/marc/record.rb
|
|
66
88
|
- lib/marc/subfield.rb
|
|
67
89
|
- lib/marc/version.rb
|
|
90
|
+
- lib/marc/writer-NEW.rb
|
|
68
91
|
- lib/marc/writer.rb
|
|
69
92
|
- lib/marc/xml_parsers.rb
|
|
70
93
|
- lib/marc/xmlreader.rb
|
|
@@ -73,14 +96,19 @@ files:
|
|
|
73
96
|
- test/bad_eacc_encoding.marc8.marc
|
|
74
97
|
- test/batch.dat
|
|
75
98
|
- test/batch.xml
|
|
99
|
+
- test/bib178448.okay.human
|
|
100
|
+
- test/bib178448.okay.marc
|
|
101
|
+
- test/bib178448.writtenout.marc
|
|
76
102
|
- test/cp866_multirecord.marc
|
|
77
103
|
- test/cp866_unimarc.marc
|
|
78
104
|
- test/escaped_character_reference.marc8.marc
|
|
105
|
+
- test/hebrew880s.marc
|
|
79
106
|
- test/marc8/data/test_marc8.txt
|
|
80
107
|
- test/marc8/data/test_utf8.txt
|
|
81
108
|
- test/marc8/tc_marc8_mapping.rb
|
|
82
109
|
- test/marc8/tc_to_unicode.rb
|
|
83
110
|
- test/marc8_accented_chars.marc
|
|
111
|
+
- test/marc_with_bad_utf8.utf8.human
|
|
84
112
|
- test/marc_with_bad_utf8.utf8.marc
|
|
85
113
|
- test/no-leading-zero.xml
|
|
86
114
|
- test/non-numeric.dat
|