1 | ## $Id: batching.py 7433 2011-12-22 07:05:32Z henrik $ |
---|
2 | ## |
---|
3 | ## Copyright (C) 2011 Uli Fouquet & Henrik Bettermann |
---|
4 | ## This program is free software; you can redistribute it and/or modify |
---|
5 | ## it under the terms of the GNU General Public License as published by |
---|
6 | ## the Free Software Foundation; either version 2 of the License, or |
---|
7 | ## (at your option) any later version. |
---|
8 | ## |
---|
9 | ## This program is distributed in the hope that it will be useful, |
---|
10 | ## but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
11 | ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
12 | ## GNU General Public License for more details. |
---|
13 | ## |
---|
14 | ## You should have received a copy of the GNU General Public License |
---|
15 | ## along with this program; if not, write to the Free Software |
---|
16 | ## Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
---|
17 | ## |
---|
18 | """Batch processing components for student objects. |
---|
19 | |
---|
20 | Batch processors eat CSV files to add, update or remove large numbers |
---|
21 | of certain kinds of objects at once. |
---|
22 | |
---|
23 | Here we define the processors for students specific objects like |
---|
24 | students, studycourses, payment tickets and accommodation tickets. |
---|
25 | """ |
---|
26 | import grok |
---|
27 | import csv |
---|
28 | from zope.interface import Interface |
---|
29 | from zope.schema import getFields |
---|
30 | from zope.component import queryUtility |
---|
31 | from zope.event import notify |
---|
32 | from zope.catalog.interfaces import ICatalog |
---|
33 | from waeup.sirp.interfaces import ( |
---|
34 | IBatchProcessor, FatalCSVError, IObjectConverter) |
---|
35 | from waeup.sirp.students.interfaces import ( |
---|
36 | IStudent, IStudentStudyCourseImport, |
---|
37 | IStudentUpdateByRegNo, IStudentUpdateByMatricNo) |
---|
38 | from waeup.sirp.utils.batching import BatchProcessor |
---|
39 | |
---|
40 | class StudentProcessor(BatchProcessor): |
---|
41 | """A batch processor for IStudent objects. |
---|
42 | """ |
---|
43 | grok.implements(IBatchProcessor) |
---|
44 | grok.provides(IBatchProcessor) |
---|
45 | grok.context(Interface) |
---|
46 | util_name = 'studentimporter' |
---|
47 | grok.name(util_name) |
---|
48 | |
---|
49 | name = u'Student Importer' |
---|
50 | iface = IStudent |
---|
51 | |
---|
52 | location_fields = [] |
---|
53 | factory_name = 'waeup.Student' |
---|
54 | |
---|
55 | mode = None |
---|
56 | |
---|
57 | @property |
---|
58 | def available_fields(self): |
---|
59 | return sorted(list(set( |
---|
60 | ['student_id','reg_number','matric_number'] + getFields( |
---|
61 | self.iface).keys()))) |
---|
62 | |
---|
63 | def checkHeaders(self, headerfields, mode='create'): |
---|
64 | if not 'reg_number' in headerfields and not 'student_id' \ |
---|
65 | in headerfields and not 'matric_number' in headerfields: |
---|
66 | raise FatalCSVError( |
---|
67 | "Need at least columns student_id or reg_number " + |
---|
68 | "or matric_number for import!") |
---|
69 | if mode == 'create': |
---|
70 | for field in self.required_fields: |
---|
71 | if not field in headerfields: |
---|
72 | raise FatalCSVError( |
---|
73 | "Need at least columns %s for import!" % |
---|
74 | ', '.join(["'%s'" % x for x in self.required_fields])) |
---|
75 | # Check for fields to be ignored... |
---|
76 | not_ignored_fields = [x for x in headerfields |
---|
77 | if not x.startswith('--')] |
---|
78 | if len(set(not_ignored_fields)) < len(not_ignored_fields): |
---|
79 | raise FatalCSVError( |
---|
80 | "Double headers: each column name may only appear once.") |
---|
81 | return True |
---|
82 | |
---|
83 | def parentsExist(self, row, site): |
---|
84 | return 'students' in site.keys() |
---|
85 | |
---|
86 | def getLocator(self, row): |
---|
87 | if row.get('student_id',None): |
---|
88 | return 'student_id' |
---|
89 | elif row.get('reg_number',None): |
---|
90 | return 'reg_number' |
---|
91 | elif row.get('matric_number',None): |
---|
92 | return 'matric_number' |
---|
93 | else: |
---|
94 | return None |
---|
95 | |
---|
96 | # The entry never exists in create mode. |
---|
97 | def entryExists(self, row, site): |
---|
98 | return self.getEntry(row, site) is not None |
---|
99 | |
---|
100 | def getParent(self, row, site): |
---|
101 | return site['students'] |
---|
102 | |
---|
103 | def getEntry(self, row, site): |
---|
104 | if not 'students' in site.keys(): |
---|
105 | return None |
---|
106 | if self.getLocator(row) == 'student_id': |
---|
107 | if row['student_id'] in site['students']: |
---|
108 | student = site['students'][row['student_id']] |
---|
109 | return student |
---|
110 | elif self.getLocator(row) == 'reg_number': |
---|
111 | reg_number = row['reg_number'] |
---|
112 | cat = queryUtility(ICatalog, name='students_catalog') |
---|
113 | results = list( |
---|
114 | cat.searchResults(reg_number=(reg_number, reg_number))) |
---|
115 | if results: |
---|
116 | return results[0] |
---|
117 | elif self.getLocator(row) == 'matric_number': |
---|
118 | matric_number = row['matric_number'] |
---|
119 | cat = queryUtility(ICatalog, name='students_catalog') |
---|
120 | results = list( |
---|
121 | cat.searchResults(matric_number=(matric_number, matric_number))) |
---|
122 | if results: |
---|
123 | return results[0] |
---|
124 | return None |
---|
125 | |
---|
126 | |
---|
127 | def addEntry(self, obj, row, site): |
---|
128 | parent = self.getParent(row, site) |
---|
129 | parent.addStudent(obj) |
---|
130 | return |
---|
131 | |
---|
132 | def delEntry(self, row, site): |
---|
133 | student = self.getEntry(row, site) |
---|
134 | if student is not None: |
---|
135 | parent = self.getParent(row, site) |
---|
136 | del parent[student.student_id] |
---|
137 | pass |
---|
138 | |
---|
139 | def getMapping(self, path, headerfields, mode): |
---|
140 | """Get a mapping from CSV file headerfields to actually used fieldnames. |
---|
141 | """ |
---|
142 | result = dict() |
---|
143 | reader = csv.reader(open(path, 'rb')) |
---|
144 | raw_header = reader.next() |
---|
145 | for num, field in enumerate(headerfields): |
---|
146 | if field not in [ |
---|
147 | 'student_id', 'reg_number', 'matric_number'] and mode == 'remove': |
---|
148 | continue |
---|
149 | if field == u'--IGNORE--': |
---|
150 | # Skip ignored columns in failed and finished data files. |
---|
151 | continue |
---|
152 | result[raw_header[num]] = field |
---|
153 | return result |
---|
154 | |
---|
155 | def checkConversion(self, row, mode='create'): |
---|
156 | """Validates all values in row. |
---|
157 | """ |
---|
158 | if mode in ['update', 'remove']: |
---|
159 | if self.getLocator(row) == 'reg_number': |
---|
160 | iface = IStudentUpdateByRegNo |
---|
161 | elif self.getLocator(row) == 'matric_number': |
---|
162 | iface = IStudentUpdateByMatricNo |
---|
163 | else: |
---|
164 | iface = self.iface |
---|
165 | converter = IObjectConverter(iface) |
---|
166 | errs, inv_errs, conv_dict = converter.fromStringDict( |
---|
167 | row, self.factory_name) |
---|
168 | return errs, inv_errs, conv_dict |
---|
169 | |
---|
170 | class StudentStudyCourseProcessor(BatchProcessor): |
---|
171 | """A batch processor for IStudentStudyCourse objects. |
---|
172 | """ |
---|
173 | grok.implements(IBatchProcessor) |
---|
174 | grok.provides(IBatchProcessor) |
---|
175 | grok.context(Interface) |
---|
176 | util_name = 'studycourseupdater' |
---|
177 | grok.name(util_name) |
---|
178 | |
---|
179 | name = u'StudentStudyCourse Importer (update only)' |
---|
180 | iface = IStudentStudyCourseImport |
---|
181 | factory_name = 'waeup.StudentStudyCourse' |
---|
182 | |
---|
183 | location_fields = [] |
---|
184 | |
---|
185 | mode = None |
---|
186 | |
---|
187 | @property |
---|
188 | def available_fields(self): |
---|
189 | return sorted(list(set( |
---|
190 | ['student_id','reg_number','matric_number'] + getFields( |
---|
191 | self.iface).keys()))) |
---|
192 | |
---|
193 | def checkHeaders(self, headerfields, mode='ignore'): |
---|
194 | if not 'reg_number' in headerfields and not 'student_id' \ |
---|
195 | in headerfields and not 'matric_number' in headerfields: |
---|
196 | raise FatalCSVError( |
---|
197 | "Need at least columns student_id " + |
---|
198 | "or reg_number or matric_number for import!") |
---|
199 | # Check for fields to be ignored... |
---|
200 | not_ignored_fields = [x for x in headerfields |
---|
201 | if not x.startswith('--')] |
---|
202 | if len(set(not_ignored_fields)) < len(not_ignored_fields): |
---|
203 | raise FatalCSVError( |
---|
204 | "Double headers: each column name may only appear once.") |
---|
205 | return True |
---|
206 | |
---|
207 | def getParent(self, row, site): |
---|
208 | if not 'students' in site.keys(): |
---|
209 | return None |
---|
210 | if 'student_id' in row.keys() and row['student_id']: |
---|
211 | if row['student_id'] in site['students']: |
---|
212 | student = site['students'][row['student_id']] |
---|
213 | return student |
---|
214 | elif 'reg_number' in row.keys() and row['reg_number']: |
---|
215 | reg_number = row['reg_number'] |
---|
216 | #import pdb; pdb.set_trace() |
---|
217 | cat = queryUtility(ICatalog, name='students_catalog') |
---|
218 | results = list( |
---|
219 | cat.searchResults(reg_number=(reg_number, reg_number))) |
---|
220 | if results: |
---|
221 | return results[0] |
---|
222 | elif 'matric_number' in row.keys() and row['matric_number']: |
---|
223 | matric_number = row['matric_number'] |
---|
224 | cat = queryUtility(ICatalog, name='students_catalog') |
---|
225 | results = list( |
---|
226 | cat.searchResults(matric_number=(matric_number, matric_number))) |
---|
227 | if results: |
---|
228 | return results[0] |
---|
229 | return None |
---|
230 | |
---|
231 | def parentsExist(self, row, site): |
---|
232 | return self.getParent(row, site) is not None |
---|
233 | |
---|
234 | def entryExists(self, row, site): |
---|
235 | student = self.getParent(row, site) |
---|
236 | if not student: |
---|
237 | return None |
---|
238 | if 'studycourse' in student: |
---|
239 | return student |
---|
240 | return None |
---|
241 | |
---|
242 | def getEntry(self, row, site): |
---|
243 | student = self.entryExists(row, site) |
---|
244 | if not student: |
---|
245 | return None |
---|
246 | return student.get('studycourse') |
---|
247 | |
---|
248 | def updateEntry(self, obj, row, site): |
---|
249 | """Update obj to the values given in row. |
---|
250 | """ |
---|
251 | for key, value in row.items(): |
---|
252 | # Skip fields not declared in interface. |
---|
253 | if hasattr(obj, key): |
---|
254 | setattr(obj, key, value) |
---|
255 | # Update the students_catalog |
---|
256 | notify(grok.ObjectModifiedEvent(obj.__parent__)) |
---|
257 | return |
---|
258 | |
---|