|
1
|
<?xml version="1.0"?>
|
|
2
|
<xs:schema targetNamespace="eml:physical-2.0.0beta8"
|
|
3
|
xmlns="eml:physical-2.0.0beta8"
|
|
4
|
xmlns:doc="eml:documentation-2.0.0beta8"
|
|
5
|
xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
|
6
|
<xs:import namespace="eml:documentation-2.0.0beta8"
|
|
7
|
schemaLocation="eml-documentation.xsd"/>
|
|
8
|
<xs:annotation>
|
|
9
|
<xs:documentation>
|
|
10
|
'$RCSfile: eml-physical.xsd,v $'
|
|
11
|
Copyright: 2000 Regents of the University of California and the
|
|
12
|
National Center for Ecological Analysis and Synthesis
|
|
13
|
For Details: http://knb.ecoinformatics.org/
|
|
14
|
|
|
15
|
'$Author: higgins $'
|
|
16
|
'$Date: 2002/04/21 22:45:30 $'
|
|
17
|
'$Revision: 1.11 $'
|
|
18
|
|
|
19
|
This program is free software; you can redistribute it and/or modify
|
|
20
|
it under the terms of the GNU General Public License as published by
|
|
21
|
the Free Software Foundation; either version 2 of the License, or
|
|
22
|
(at your option) any later version.
|
|
23
|
|
|
24
|
This program is distributed in the hope that it will be useful,
|
|
25
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
26
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
27
|
GNU General Public License for more details.
|
|
28
|
|
|
29
|
You should have received a copy of the GNU General Public License
|
|
30
|
along with this program; if not, write to the Free Software
|
|
31
|
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
32
|
</xs:documentation>
|
|
33
|
<xs:appinfo>
|
|
34
|
<doc:moduleName>eml-physical</doc:moduleName>
|
|
35
|
<doc:moduleDescription>
|
|
36
|
The eml-physical Module defines the structural
|
|
37
|
characteristics of data formats as delivered over the wire or
|
|
38
|
as found in a file system. One physical object (which can be a
|
|
39
|
bytestream or an object in a file system) might contain multiple
|
|
40
|
entities (for example, this would be typical in a MS Access file
|
|
41
|
that contained multiple tables of data). However, it is typically
|
|
42
|
used to describe a file or stream that is in some text-based
|
|
43
|
format such as ASCII or UTF-8, and includes the information needed
|
|
44
|
to parse the data stream to extract the entity and its attributes
|
|
45
|
from the stream.
|
|
46
|
</doc:moduleDescription>
|
|
47
|
</xs:appinfo>
|
|
48
|
</xs:annotation>
|
|
49
|
<xs:element name="eml-physical">
|
|
50
|
<xs:annotation>
|
|
51
|
<xs:appinfo>
|
|
52
|
<doc:tooltip>Physical structure. </doc:tooltip>
|
|
53
|
<doc:summary>Physical structure of an entity or entities.</doc:summary>
|
|
54
|
<doc:description>
|
|
55
|
Physical structure of an entity or entities. This generally is a detailed
|
|
56
|
description of a text representation that shows how the columns and rows
|
|
57
|
of a table are represented, or simply the name of a well-known binary or
|
|
58
|
proprietary format (e.g., Microsoft Excel 2000).
|
|
59
|
</doc:description>
|
|
60
|
<doc:example/>
|
|
61
|
<doc:lineage>
|
|
62
|
The eml-physical was introduced into EML 1.4 as eml-file.
|
|
63
|
</doc:lineage>
|
|
64
|
</xs:appinfo>
|
|
65
|
</xs:annotation>
|
|
66
|
<xs:complexType>
|
|
67
|
<xs:sequence>
|
|
68
|
<xs:element name="identifier" maxOccurs="unbounded">
|
|
69
|
<xs:annotation>
|
|
70
|
<xs:appinfo>
|
|
71
|
<doc:tooltip>
|
|
72
|
Unique identifier
|
|
73
|
</doc:tooltip>
|
|
74
|
<doc:summary>
|
|
75
|
The unique identifier of this metadata file or object.
|
|
76
|
</doc:summary>
|
|
77
|
<doc:description>
|
|
78
|
The identifier field provides a unique identifier for this
|
|
79
|
metadata documentation. It will most likely be part of a
|
|
80
|
sequence of numbers or letters that are meaningful in a
|
|
81
|
larger context, such as a metadata catalog. That larger
|
|
82
|
system can be identified in the "system" attribute. Multiple
|
|
83
|
identifiers can be listed corresponding to different catalog
|
|
84
|
systems.
|
|
85
|
</doc:description>
|
|
86
|
<doc:example><![CDATA[<identifier system="metacat">nceas.3.2</identifier>]]></doc:example>
|
|
87
|
<doc:lineage>
|
|
88
|
The 'identifier' field is derived from the eml-dataset
|
|
89
|
meta_file_id filed in EML 1.4.
|
|
90
|
</doc:lineage>
|
|
91
|
</xs:appinfo>
|
|
92
|
</xs:annotation>
|
|
93
|
<xs:complexType>
|
|
94
|
<xs:simpleContent>
|
|
95
|
<xs:extension base="xs:string">
|
|
96
|
<xs:attribute name="system" type="xs:string" use="optional">
|
|
97
|
<xs:annotation>
|
|
98
|
<xs:appinfo>
|
|
99
|
<doc:tooltip>
|
|
100
|
Catalog system
|
|
101
|
</doc:tooltip>
|
|
102
|
<doc:summary>
|
|
103
|
The catalog system in which this identifier is used.
|
|
104
|
</doc:summary>
|
|
105
|
<doc:description>
|
|
106
|
This element gives the name of the catalog system in which
|
|
107
|
this identifier is used. It is useful to determine the
|
|
108
|
scope of the identifier, and to determine the semantics
|
|
109
|
of the various subparts of the identifier. Unresolved issue:
|
|
110
|
can or should this be a URI/URL pointing to the catalog
|
|
111
|
system, or just the name?
|
|
112
|
</doc:description>
|
|
113
|
<doc:example><![CDATA[
|
|
114
|
<identifier system="metacat">nceas.3.2</identifier>]]></doc:example>
|
|
115
|
<doc:lineage>
|
|
116
|
New to EML 2.0.
|
|
117
|
</doc:lineage>
|
|
118
|
</xs:appinfo>
|
|
119
|
</xs:annotation>
|
|
120
|
</xs:attribute>
|
|
121
|
</xs:extension>
|
|
122
|
</xs:simpleContent>
|
|
123
|
</xs:complexType>
|
|
124
|
</xs:element>
|
|
125
|
<xs:element name="format">
|
|
126
|
<xs:annotation>
|
|
127
|
<xs:appinfo>
|
|
128
|
<doc:tooltip>
|
|
129
|
File format
|
|
130
|
</doc:tooltip>
|
|
131
|
<doc:summary>
|
|
132
|
Contains the name of the format for this file.
|
|
133
|
</doc:summary>
|
|
134
|
<doc:description>
|
|
135
|
This element contains the name of the file's format.
|
|
136
|
The file's format is typically ASCII, Unicode, or some
|
|
137
|
well-known binary format (e.g., Microsoft Excel 2000).
|
|
138
|
It is recommended to include a
|
|
139
|
complete MIME type here, such as image/jpeg or text/xml. Note
|
|
140
|
that this is the format of the physical file itself.
|
|
141
|
</doc:description>
|
|
142
|
<doc:example><![CDATA[<format>ASCII</format>]]></doc:example>
|
|
143
|
<doc:lineage>
|
|
144
|
The format element was introduced into EML 1.4.
|
|
145
|
</doc:lineage>
|
|
146
|
</xs:appinfo>
|
|
147
|
</xs:annotation>
|
|
148
|
|
|
149
|
<xs:complexType>
|
|
150
|
<xs:simpleContent>
|
|
151
|
<xs:extension base="xs:string">
|
|
152
|
<xs:attribute name="version" type="xs:string" use="optional">
|
|
153
|
<xs:annotation>
|
|
154
|
<xs:appinfo>
|
|
155
|
<doc:tooltip>
|
|
156
|
</doc:tooltip>
|
|
157
|
<doc:summary>
|
|
158
|
</doc:summary>
|
|
159
|
<doc:description>
|
|
160
|
This attribute is designed for use in providing the
|
|
161
|
version of the format in use. For example, 'Excel'
|
|
162
|
might be the format; with '3.1' being the version
|
|
163
|
</doc:description>
|
|
164
|
<doc:example></doc:example>
|
|
165
|
<doc:lineage>
|
|
166
|
New to EML 2.0.
|
|
167
|
</doc:lineage>
|
|
168
|
</xs:appinfo>
|
|
169
|
</xs:annotation>
|
|
170
|
</xs:attribute>
|
|
171
|
<xs:attribute name="citation" type="xs:string" use="optional">
|
|
172
|
<xs:annotation>
|
|
173
|
<xs:appinfo>
|
|
174
|
<doc:tooltip>
|
|
175
|
</doc:tooltip>
|
|
176
|
<doc:summary>
|
|
177
|
</doc:summary>
|
|
178
|
<doc:description>
|
|
179
|
Citation is a simple reference describing the format
|
|
180
|
where one can find a detailed description of the
|
|
181
|
format.
|
|
182
|
</doc:description>
|
|
183
|
<doc:example></doc:example>
|
|
184
|
<doc:lineage>
|
|
185
|
New to EML 2.0.
|
|
186
|
</doc:lineage>
|
|
187
|
</xs:appinfo>
|
|
188
|
</xs:annotation>
|
|
189
|
</xs:attribute>
|
|
190
|
</xs:extension>
|
|
191
|
</xs:simpleContent>
|
|
192
|
</xs:complexType>
|
|
193
|
|
|
194
|
</xs:element>
|
|
195
|
|
|
196
|
<xs:element name="objectName" type="xs:string" minOccurs="0"/>
|
|
197
|
|
|
198
|
<xs:element name="characterEncoding" type="xs:string" minOccurs="0">
|
|
199
|
<xs:annotation>
|
|
200
|
<xs:appinfo>
|
|
201
|
<doc:tooltip>
|
|
202
|
Character Encoding
|
|
203
|
</doc:tooltip>
|
|
204
|
<doc:summary>
|
|
205
|
Contains the name of the chracter encoding used for the data.
|
|
206
|
</doc:summary>
|
|
207
|
<doc:description>
|
|
208
|
This element contains the name of the character encoding.
|
|
209
|
This is typically ASCII or UTF-8, or one of the other common encodings.
|
|
210
|
</doc:description>
|
|
211
|
<doc:example><![CDATA[<characterEncoding>UTF-8</characterEncoding>]]></doc:example>
|
|
212
|
<doc:lineage>
|
|
213
|
Introduced in EML 2.0
|
|
214
|
</doc:lineage>
|
|
215
|
</xs:appinfo>
|
|
216
|
</xs:annotation>
|
|
217
|
</xs:element>
|
|
218
|
<xs:element name="size" minOccurs="0">
|
|
219
|
<xs:annotation>
|
|
220
|
<xs:appinfo>
|
|
221
|
<doc:tooltip>
|
|
222
|
Entity size
|
|
223
|
</doc:tooltip>
|
|
224
|
<doc:summary>
|
|
225
|
Describes the physical size of the entity.
|
|
226
|
</doc:summary>
|
|
227
|
<doc:description>
|
|
228
|
This element contains information of the physical size
|
|
229
|
of the entity, typically in bytes.
|
|
230
|
</doc:description>
|
|
231
|
<doc:example><![CDATA[<entitySize unit="bytes">13</entitySize>]]></doc:example>
|
|
232
|
<doc:lineage>
|
|
233
|
The entitySize was introduced into EML 1.4.
|
|
234
|
</doc:lineage>
|
|
235
|
</xs:appinfo>
|
|
236
|
</xs:annotation>
|
|
237
|
<xs:complexType>
|
|
238
|
<xs:simpleContent>
|
|
239
|
<xs:extension base="xs:string">
|
|
240
|
<xs:attribute name="unit" use="required" default="bytes">
|
|
241
|
<xs:annotation>
|
|
242
|
<xs:appinfo>
|
|
243
|
<doc:tooltip>
|
|
244
|
Unit of measurement
|
|
245
|
</doc:tooltip>
|
|
246
|
<doc:summary>
|
|
247
|
Unit of measurement for the entity size, typically bytes
|
|
248
|
</doc:summary>
|
|
249
|
<doc:description>
|
|
250
|
This element gives the unit of measurement for the
|
|
251
|
size of the entity, and is typically bytes.
|
|
252
|
</doc:description>
|
|
253
|
<doc:example><![CDATA[<entitySize unit="bytes">13</entitySize>]]></doc:example>
|
|
254
|
<doc:lineage>
|
|
255
|
The unit was introduced into EML 1.4.
|
|
256
|
</doc:lineage>
|
|
257
|
</xs:appinfo>
|
|
258
|
</xs:annotation>
|
|
259
|
</xs:attribute>
|
|
260
|
</xs:extension>
|
|
261
|
</xs:simpleContent>
|
|
262
|
</xs:complexType>
|
|
263
|
</xs:element>
|
|
264
|
<xs:element name="authentication" minOccurs="0" maxOccurs="unbounded">
|
|
265
|
<xs:annotation>
|
|
266
|
<xs:appinfo>
|
|
267
|
<doc:tooltip>
|
|
268
|
Authentication method
|
|
269
|
</doc:tooltip>
|
|
270
|
<doc:summary>
|
|
271
|
A value, typically a checksum, used to authenticate that the bitstream
|
|
272
|
delivered to the user is identical to the original.
|
|
273
|
</doc:summary>
|
|
274
|
<doc:description>
|
|
275
|
This element describes authentication procedures or
|
|
276
|
techniques, typically by giving a checksum method (e.g., MD5) and
|
|
277
|
checksum value for the bytestream.
|
|
278
|
</doc:description>
|
|
279
|
<doc:example>
|
|
280
|
<![CDATA[
|
|
281
|
<authentication method="MD5">f5b2177ea03aea73de12da81f896fe40</authentication>
|
|
282
|
]]>
|
|
283
|
</doc:example>
|
|
284
|
<doc:lineage>
|
|
285
|
The authentication element was introduced into EML 1.4.
|
|
286
|
</doc:lineage>
|
|
287
|
</xs:appinfo>
|
|
288
|
</xs:annotation>
|
|
289
|
<xs:complexType>
|
|
290
|
<xs:simpleContent>
|
|
291
|
<xs:extension base="xs:string">
|
|
292
|
<xs:attribute name="method" type="xs:string" use="optional">
|
|
293
|
<xs:annotation>
|
|
294
|
<xs:appinfo>
|
|
295
|
<doc:tooltip>
|
|
296
|
Authentication method
|
|
297
|
</doc:tooltip>
|
|
298
|
<doc:summary>
|
|
299
|
The method used to calculate an authentication checksum.
|
|
300
|
</doc:summary>
|
|
301
|
<doc:description>
|
|
302
|
This element names the method used to calculate and
|
|
303
|
authentication checksum that can be used to validate a
|
|
304
|
bytestream. Typical checksum methods include MD5 and CRC.
|
|
305
|
</doc:description>
|
|
306
|
<doc:example>
|
|
307
|
<![CDATA[
|
|
308
|
<authentication method="MD5">f5b2177ea03aea73de12da81f896fe40</authentication>
|
|
309
|
]]>
|
|
310
|
</doc:example>
|
|
311
|
<doc:lineage>
|
|
312
|
The authentication element was introduced into EML 1.4.
|
|
313
|
</doc:lineage>
|
|
314
|
</xs:appinfo>
|
|
315
|
</xs:annotation>
|
|
316
|
</xs:attribute>
|
|
317
|
</xs:extension>
|
|
318
|
</xs:simpleContent>
|
|
319
|
</xs:complexType>
|
|
320
|
</xs:element>
|
|
321
|
<xs:element name="compressionMethod" type="xs:string" minOccurs="0">
|
|
322
|
<xs:annotation>
|
|
323
|
<xs:appinfo>
|
|
324
|
<doc:tooltip>
|
|
325
|
Entity's compression method
|
|
326
|
</doc:tooltip>
|
|
327
|
<doc:summary>
|
|
328
|
Name ofthe entity's compression method
|
|
329
|
</doc:summary>
|
|
330
|
<doc:description>
|
|
331
|
This element describes any compression methods used to
|
|
332
|
compress the entity, such as zip, compress, etc.
|
|
333
|
</doc:description>
|
|
334
|
<doc:example/>
|
|
335
|
<doc:lineage>
|
|
336
|
The compressed element was introduced into EML 1.4.
|
|
337
|
</doc:lineage>
|
|
338
|
</xs:appinfo>
|
|
339
|
</xs:annotation>
|
|
340
|
</xs:element>
|
|
341
|
<xs:element name="encodingMethod" type="xs:string" minOccurs="0">
|
|
342
|
<xs:annotation>
|
|
343
|
<xs:appinfo>
|
|
344
|
<doc:tooltip>
|
|
345
|
Encoding Method
|
|
346
|
</doc:tooltip>
|
|
347
|
<doc:summary>
|
|
348
|
Method used for encoding the entity
|
|
349
|
</doc:summary>
|
|
350
|
<doc:description>
|
|
351
|
This element describes the entity's encoded method, such as
|
|
352
|
MIME base64 encoding or binhex encoding.
|
|
353
|
</doc:description>
|
|
354
|
<doc:example/>
|
|
355
|
<doc:lineage>
|
|
356
|
The encoded element was introduced into EML 1.4.
|
|
357
|
</doc:lineage>
|
|
358
|
</xs:appinfo>
|
|
359
|
</xs:annotation>
|
|
360
|
</xs:element>
|
|
361
|
<xs:element name="numHeaderLines" type="xs:string" minOccurs="0">
|
|
362
|
<xs:annotation>
|
|
363
|
<xs:appinfo>
|
|
364
|
<doc:tooltip>
|
|
365
|
Header lines
|
|
366
|
</doc:tooltip>
|
|
367
|
<doc:summary>
|
|
368
|
Header lines in the entity
|
|
369
|
</doc:summary>
|
|
370
|
<doc:description>
|
|
371
|
Number of header lines or information that prepares data.
|
|
372
|
</doc:description>
|
|
373
|
<doc:example><![CDATA[<numHeaderLines>3</numHeaderLines>]]></doc:example>
|
|
374
|
<doc:lineage>
|
|
375
|
The numHeaderLines element was introduced into EML 1.4.
|
|
376
|
</doc:lineage>
|
|
377
|
</xs:appinfo>
|
|
378
|
</xs:annotation>
|
|
379
|
</xs:element>
|
|
380
|
<xs:element name="recordDelimiter" type="xs:string" minOccurs="0">
|
|
381
|
<xs:annotation>
|
|
382
|
<xs:appinfo>
|
|
383
|
<doc:tooltip>
|
|
384
|
Record delimiter character
|
|
385
|
</doc:tooltip>
|
|
386
|
<doc:summary>
|
|
387
|
Character used to delimit records.
|
|
388
|
</doc:summary>
|
|
389
|
<doc:description>
|
|
390
|
This element specifies the record delimiter character
|
|
391
|
when the format is text. The record delimiter is usually a
|
|
392
|
newline (\n) on UNIX, a carriage return (\r) on MacOS, or
|
|
393
|
both (\r\n) on Windows/DOS. Multiline records are usually
|
|
394
|
delimited with two line ending characters, for example on UNIX
|
|
395
|
it would be two newline characters (\n\n).
|
|
396
|
</doc:description>
|
|
397
|
<doc:example><![CDATA[<recordDelimiter>\n\r</recordDelimiter>]]></doc:example>
|
|
398
|
<doc:lineage>
|
|
399
|
The recordDelimiter element was introduced into EML 1.4.
|
|
400
|
</doc:lineage>
|
|
401
|
</xs:appinfo>
|
|
402
|
</xs:annotation>
|
|
403
|
</xs:element>
|
|
404
|
<xs:element name="maxRecordLength" type="xs:string" minOccurs="0"/>
|
|
405
|
<xs:element name="quoteCharacter" type="xs:string" minOccurs="0" maxOccurs="unbounded">
|
|
406
|
<xs:annotation>
|
|
407
|
<xs:appinfo>
|
|
408
|
<doc:tooltip>
|
|
409
|
Quote character
|
|
410
|
</doc:tooltip>
|
|
411
|
<doc:summary>
|
|
412
|
Character used to quote values for delimeter escaping
|
|
413
|
</doc:summary>
|
|
414
|
<doc:description>
|
|
415
|
This element specifies a character to be used in the entity
|
|
416
|
for quoting values so that field delimeters can be used within
|
|
417
|
the value. This basically allows delimeter "escaping". The
|
|
418
|
quoteChacter is typically a " or '.
|
|
419
|
</doc:description>
|
|
420
|
<doc:example><![CDATA[<quoteCharacter>"</quoteCharacter>]]></doc:example>
|
|
421
|
<doc:lineage>
|
|
422
|
The quoteCharacter element was taken from the NBII standard.
|
|
423
|
</doc:lineage>
|
|
424
|
</xs:appinfo>
|
|
425
|
</xs:annotation>
|
|
426
|
</xs:element>
|
|
427
|
<xs:element name="literalCharacter" type="xs:string" minOccurs="0" maxOccurs="unbounded">
|
|
428
|
<xs:annotation>
|
|
429
|
<xs:appinfo>
|
|
430
|
<doc:tooltip>
|
|
431
|
Literal character
|
|
432
|
</doc:tooltip>
|
|
433
|
<doc:summary>
|
|
434
|
Character used to escape other characters
|
|
435
|
</doc:summary>
|
|
436
|
<doc:description>
|
|
437
|
This element specifies a character to be used for escaping
|
|
438
|
character values so that the following character is treated as its literal
|
|
439
|
value. This allows "escaping" for special characters like quotes, commas,
|
|
440
|
and spaces when they aren't intended as a delimiter value. The
|
|
441
|
literalChacter is typically a \.
|
|
442
|
</doc:description>
|
|
443
|
<doc:example><![CDATA[<literalCharacter>\</literalCharacter>]]></doc:example>
|
|
444
|
<doc:lineage>
|
|
445
|
Introduced in EML 2.0.
|
|
446
|
</doc:lineage>
|
|
447
|
</xs:appinfo>
|
|
448
|
</xs:annotation>
|
|
449
|
</xs:element>
|
|
450
|
<xs:sequence minOccurs="0" maxOccurs="unbounded">
|
|
451
|
<xs:element name="fieldStartColumn" type="xs:string" minOccurs="0">
|
|
452
|
<xs:annotation>
|
|
453
|
<xs:appinfo>
|
|
454
|
<doc:tooltip>
|
|
455
|
Start column
|
|
456
|
</doc:tooltip>
|
|
457
|
<doc:summary>
|
|
458
|
The starting column number for a fixed format attribute.
|
|
459
|
</doc:summary>
|
|
460
|
<doc:description>
|
|
461
|
FixedWidth fields have a set length, thus
|
|
462
|
the end of the field can always be determined
|
|
463
|
by adding the fieldWidth to the starting
|
|
464
|
column number.
|
|
465
|
</doc:description>
|
|
466
|
<doc:example>
|
|
467
|
any positive integer, see example in "delimeter" description
|
|
468
|
</doc:example>
|
|
469
|
<doc:lineage>
|
|
470
|
Introduced into EML 2.0.
|
|
471
|
</doc:lineage>
|
|
472
|
</xs:appinfo>
|
|
473
|
</xs:annotation>
|
|
474
|
</xs:element>
|
|
475
|
<xs:choice>
|
|
476
|
<xs:element name="fieldWidth" type="xs:string">
|
|
477
|
<xs:annotation>
|
|
478
|
<xs:appinfo>
|
|
479
|
<doc:tooltip>
|
|
480
|
Field width
|
|
481
|
</doc:tooltip>
|
|
482
|
<doc:summary>
|
|
483
|
FieldWidth specification for fixed field length.
|
|
484
|
</doc:summary>
|
|
485
|
<doc:description>
|
|
486
|
FixedWidth fields have a set length, thus
|
|
487
|
the end of the field can always be determined
|
|
488
|
by adding the fieldWidth to the starting
|
|
489
|
column number.
|
|
490
|
</doc:description>
|
|
491
|
<doc:example>
|
|
492
|
any positive integer, see example in "delimeter"
|
|
493
|
description
|
|
494
|
</doc:example>
|
|
495
|
<doc:lineage>
|
|
496
|
The fieldWidth element was introduced into
|
|
497
|
EML 1.4. Semantics changed to work identically to
|
|
498
|
the NBII DTD.
|
|
499
|
</doc:lineage>
|
|
500
|
</xs:appinfo>
|
|
501
|
</xs:annotation>
|
|
502
|
</xs:element>
|
|
503
|
<xs:element name="fieldDelimiter" type="xs:string">
|
|
504
|
<xs:annotation>
|
|
505
|
<xs:appinfo>
|
|
506
|
<doc:tooltip>
|
|
507
|
Attribute delimiter
|
|
508
|
</doc:tooltip>
|
|
509
|
<doc:summary>
|
|
510
|
The end of the attribute (field) is delimited by a
|
|
511
|
special character called a field delimiter.
|
|
512
|
</doc:summary>
|
|
513
|
<doc:description>
|
|
514
|
Variable width format fields (attributes) can vary in their
|
|
515
|
field length, thus the end of the field is
|
|
516
|
delimited by a special character called a
|
|
517
|
field delimiter (typically a comma or a space).
|
|
518
|
|
|
519
|
Data sets are generally classified as fixedWidth
|
|
520
|
format or variableWidth format, but we have
|
|
521
|
determined that this is actually a per-field
|
|
522
|
classification because one may encounter
|
|
523
|
fixedWidth fields mixed together in the same
|
|
524
|
data file with variableWidth fields.
|
|
525
|
|
|
526
|
In our encoding scheme, the start of each field
|
|
527
|
is assumed to be the column after the last column
|
|
528
|
of the previous field, or the first column
|
|
529
|
if this is the first field in the dataset, unless
|
|
530
|
the starting column is explicity enumerated using the
|
|
531
|
"fieldStartColumn" element.
|
|
532
|
The end column for each field is classified
|
|
533
|
using either a special character delimeter indicated
|
|
534
|
using the filedDelimiter element,
|
|
535
|
or a fixed field length indicated by using the "fieldWidth"
|
|
536
|
element. The delimiter for the last field in the data set can be omitted.
|
|
537
|
variableWidth fields can vary in their field length, and the end of
|
|
538
|
the field is delimited by a special character
|
|
539
|
called a field delimiter, usually a comma or
|
|
540
|
a tab character. fixedWidth fields have a set
|
|
541
|
length, and so the end of the field can always
|
|
542
|
be determined by adding the fieldWidth to the
|
|
543
|
starting column number. Here is an example:
|
|
544
|
|
|
545
|
Assume we have the following data in a data set:
|
|
546
|
|
|
547
|
May,100aaaa,1.2,
|
|
548
|
April,200aaaa,3.4,
|
|
549
|
June,300bbbb,4.6,
|
|
550
|
|
|
551
|
The metadata indicating the physical layout of the 4 fields would include the
|
|
552
|
following:
|
|
553
|
|
|
554
|
<![CDATA[
|
|
555
|
<delimiter>,</delimiter>
|
|
556
|
<fieldWidth>3</fieldWidth>
|
|
557
|
<fieldWidth>3</fieldWidth>
|
|
558
|
<delimiter>,</delimiter>
|
|
559
|
]]>
|
|
560
|
|
|
561
|
In a strictly fixed format file, the metadata would be slightly different:
|
|
562
|
|
|
563
|
May100aaaa1.2
|
|
564
|
Apr200aaaa3.4
|
|
565
|
Jun300bbbb4.6
|
|
566
|
|
|
567
|
<![CDATA[
|
|
568
|
<fieldWidth>3</fieldWidth>
|
|
569
|
<fieldWidth>3</fieldWidth>
|
|
570
|
<fieldWidth>4</fieldWidth>
|
|
571
|
<fieldWidth>3</fieldWidth>
|
|
572
|
]]>
|
|
573
|
|
|
574
|
or, one could explicitly describe the starting columns:
|
|
575
|
|
|
576
|
<![CDATA[
|
|
577
|
<fieldStartColumn>1</fieldStartColumn>
|
|
578
|
<fieldWidth>3</fieldWidth>
|
|
579
|
<fieldStartColumn>4</fieldStartColumn>
|
|
580
|
<fieldWidth>3</fieldWidth>
|
|
581
|
<fieldStartColumn>7</fieldStartColumn>
|
|
582
|
<fieldWidth>4</fieldWidth>
|
|
583
|
<fieldStartColumn>11</fieldStartColumn>
|
|
584
|
<fieldWidth>3</fieldWidth>
|
|
585
|
]]></doc:description>
|
|
586
|
<doc:example>
|
|
587
|
comma, tab, white space, etc.
|
|
588
|
</doc:example>
|
|
589
|
<doc:lineage>
|
|
590
|
The delimiter element was introduced into
|
|
591
|
EML 1.4. Semantics changed to work identically to
|
|
592
|
the NBII DTD, and then modified to fit more cases.
|
|
593
|
</doc:lineage>
|
|
594
|
</xs:appinfo>
|
|
595
|
</xs:annotation>
|
|
596
|
</xs:element>
|
|
597
|
</xs:choice>
|
|
598
|
</xs:sequence>
|
|
599
|
|
|
600
|
<xs:element name="BinaryRasterInfo" minOccurs="0">
|
|
601
|
<xs:complexType>
|
|
602
|
<xs:sequence>
|
|
603
|
<xs:element name="nrows" type="xs:int"/>
|
|
604
|
<xs:element name="ncols" type="xs:int"/>
|
|
605
|
<xs:element name="nbands" type="xs:int"/>
|
|
606
|
<xs:element name="nbits"/>
|
|
607
|
<xs:element name="byteorder"/>
|
|
608
|
<xs:element name="layout"/>
|
|
609
|
<xs:element name="skipbytes"/>
|
|
610
|
<xs:element name="ulxmap"/>
|
|
611
|
<xs:element name="ulymap"/>
|
|
612
|
<xs:element name="xdim"/>
|
|
613
|
<xs:element name="ydim"/>
|
|
614
|
<xs:element name="bandrowbytes"/>
|
|
615
|
<xs:element name="totalrowbytes"/>
|
|
616
|
<xs:element name="bandgapbytes"/>
|
|
617
|
</xs:sequence>
|
|
618
|
</xs:complexType>
|
|
619
|
</xs:element>
|
|
620
|
|
|
621
|
</xs:sequence>
|
|
622
|
</xs:complexType>
|
|
623
|
</xs:element>
|
|
624
|
</xs:schema>
|