-
Notifications
You must be signed in to change notification settings - Fork 0
/
PositionalIndex.java
483 lines (424 loc) · 20.3 KB
/
PositionalIndex.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
/*
This program constructs positional indexes
and processing phrase and proximity queries
from a large document corpus (over 30,000
documents) from Project Gutenberg. Query
results are stored in CSV files for ease of
reading through spreadsheet software.
Authors: Abelson Abueg
Date Created: 11 Mar 2022
Last Updated: 13 Mar 2022
*/
// Java
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.BufferedReader;
import java.io.PrintWriter;
import java.io.UnsupportedEncodingException;
import java.io.IOException;
import java.util.regex.Pattern;
import java.util.ArrayList;
import java.util.Map;
import java.util.Set;
import java.util.TreeMap;
import java.util.regex.Matcher;
public class PositionalIndex {
/*
*
* CONSTRUCTOR AND CLASS METHODS
*
*/
// TreeMap<Term, DocumentList<DocID, PositionalListing<ListingIndex, DocIndex>>>
private TreeMap<String, TreeMap<Integer, TreeMap<Integer, Integer>>> positionalIndexData;
// Default Constructor; it's all you really need.
public PositionalIndex() {
this.positionalIndexData = new TreeMap<String, TreeMap<Integer, TreeMap<Integer, Integer>>>();
}
public void updatePositionalIndex(String term, int docID, int docPosition) {
// If the term exists in the Positional Index Data
if (this.positionalIndexData.containsKey(term)) {
// If the document exists in the Positional Index Data
if (this.positionalIndexData.get(term).containsKey(docID)) {
this.positionalIndexData.get(term).get(docID).put(
/*
* size will be the size before insertion providing 0-based indexing
* for the key in the positional listing.
*/
this.positionalIndexData.get(term).get(docID).size(), docPosition);
} else {
// Create new Positional List
TreeMap<Integer, Integer> newPositionalList = new TreeMap<Integer, Integer>();
// Insert new position into the new Positional List
newPositionalList.put(newPositionalList.size(), docPosition);
// Insert new document into the Document List
this.positionalIndexData.get(term).put(docID, newPositionalList);
}
} else {
// Create new Positional List
TreeMap<Integer, Integer> newPositionalList = new TreeMap<Integer, Integer>();
// Insert new position into the new Positional List
newPositionalList.put(newPositionalList.size(), docPosition);
// Create a new Document List
TreeMap<Integer, TreeMap<Integer, Integer>> newDocumentList = new TreeMap<Integer, TreeMap<Integer, Integer>>();
// Insert new Document with Positional List into Document List
newDocumentList.put(docID, newPositionalList);
// Insert new Document List into the Term TreeMap
this.positionalIndexData.put(term, newDocumentList);
}
}
int getTermCount() {
return this.positionalIndexData.size();
}
int getDocumentCountByTerm(String term) {
return this.positionalIndexData.get(term).size();
}
int getPositionalCountByTermAndDocID(String term, int docID) {
return this.positionalIndexData.get(term).get(docID).size();
}
// Print the stats of the PositionalIndex object.
void printStats() {
System.out.println("Number of Terms: " + this.getTermCount());
Set<Map.Entry<String, TreeMap<Integer, TreeMap<Integer, Integer>>>> termEntry = this.positionalIndexData
.entrySet();
termEntry.forEach(term -> {
Set<Map.Entry<Integer, TreeMap<Integer, Integer>>> docEntry = term.getValue().entrySet();
System.out.println("\t" + term.getKey() + ": " + term.getValue().size());
docEntry.forEach(doc -> {
System.out.println("\t\t" + doc.getKey() + ": " + doc.getValue().size());
});
});
}
// Searches for phrases between two queried words within k words and print
// result into CSV file. Handles both directions.
void proximitySearch(String x, String y, int k) {
// Case where term doesn't exist.
if (this.positionalIndexData.get(x) != null && this.positionalIndexData.get(y) != null) {
// Create a String ArrayList for storing the result and have it sorted.
ArrayList<String> xFirstResults = new ArrayList<String>();
ArrayList<String> yFirstResults = new ArrayList<String>();
// Get the Document List from the Terms
TreeMap<Integer, TreeMap<Integer, Integer>> xDocList = this.positionalIndexData.get(x);
TreeMap<Integer, TreeMap<Integer, Integer>> yDocList = this.positionalIndexData.get(y);
// For iterating at the DocList level.
Set<Map.Entry<Integer, TreeMap<Integer, Integer>>> xEntry = xDocList.entrySet();
Set<Map.Entry<Integer, TreeMap<Integer, Integer>>> yEntry = yDocList.entrySet();
// Handle x...y
xEntry.forEach(doc -> {
if (yDocList.get(doc.getKey()) != null) {
// For iterating at Positional Listing level.
Set<Map.Entry<Integer, Integer>> xPositionEntry = doc.getValue().entrySet();
Set<Map.Entry<Integer, Integer>> yPositionEntry = yDocList.get(doc.getKey()).entrySet();
xPositionEntry.forEach(xPosition -> {
yPositionEntry.forEach(yPosition -> {
if (xPosition.getValue() + (k) == yPosition.getValue()) {
xFirstResults.add(
doc.getKey() + "," + xPosition.getValue() + "," + yPosition.getValue());
}
});
});
}
});
// Handle y...x
yEntry.forEach(doc -> {
if (xDocList.get(doc.getKey()) != null) {
// For iterating at Positional Listing level.
Set<Map.Entry<Integer, Integer>> yPositionEntry = doc.getValue().entrySet();
Set<Map.Entry<Integer, Integer>> xPositionEntry = xDocList.get(doc.getKey()).entrySet();
yPositionEntry.forEach(yPosition -> {
xPositionEntry.forEach(xPosition -> {
if (yPosition.getValue() + (k) == xPosition.getValue()) {
yFirstResults.add(
doc.getKey() + "," + yPosition.getValue() + "," + xPosition.getValue());
}
});
});
}
});
// Skip if ArrayLists are empty
if (!xFirstResults.isEmpty() || !yFirstResults.isEmpty()) {
System.out.println("Writing results into CSV files...");
PrintWriter resultWriter = null;
PrintWriter detailedWriter = null;
try {
resultWriter = new PrintWriter(outputPath + "\\" + x + "_" + y + "_" + k + "_" + outputFiles[0],
"UTF-8");
detailedWriter = new PrintWriter(outputPath + "\\" + x + "_" + y + "_" + k + "_" + outputFiles[1],
"UTF-8");
} catch (IOException ex) {
System.err.println(ex);
System.err.println("Program terminated\n");
System.exit(1);
}
// Print CSV Headers
resultWriter.println("DocID,First Position,Second Position");
detailedWriter.println("DocID,Filepath,First Position,Second Position,Exact Phrase");
// Handle x...y
for (String triple : xFirstResults) {
resultWriter.println(triple);
String[] splitTriple = triple.split(",");
String phrase = "";
int position = 0;
// Get exact phrase
try {
Pattern wordPattern = Pattern.compile("[a-zA-Z]+");
Matcher wordMatcher;
String line, word = "";
BufferedReader br = new BufferedReader(
new FileReader(inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1)));
while ((line = br.readLine()) != null && position < Integer.parseInt(splitTriple[2])) {
// process the line by extracting words using the wordPattern
wordMatcher = wordPattern.matcher(line);
// Process one word at a time
while (wordMatcher.find()) {
position++;
// Extract and convert the word to lowercase
word = line.substring(wordMatcher.start(), wordMatcher.end());
if (position >= Integer.parseInt(splitTriple[1])
&& position <= Integer.parseInt(splitTriple[2])) {
phrase = phrase + " " + word;
}
} // while - wordMatcher
} // while - Line
} catch (IOException ex) {
System.err.println("File " + inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1)
+ " not found. Program terminated.\n");
System.exit(1);
}
detailedWriter.println(splitTriple[0] + "," +
inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1) + "," +
splitTriple[1] + "," +
splitTriple[2] + "," +
phrase.trim());
}
// Handle y...x
for (String triple : yFirstResults) {
resultWriter.println(triple);
String[] splitTriple = triple.split(",");
String phrase = "";
int position = 0;
// Get exact phrase
try {
Pattern wordPattern = Pattern.compile("[a-zA-Z]+");
Matcher wordMatcher;
String line, word = "";
BufferedReader br = new BufferedReader(
new FileReader(inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1)));
while ((line = br.readLine()) != null && position < Integer.parseInt(splitTriple[2])) {
// process the line by extracting words using the wordPattern
wordMatcher = wordPattern.matcher(line);
// Process one word at a time
while (wordMatcher.find()) {
position++;
// Extract and convert the word to lowercase
word = line.substring(wordMatcher.start(), wordMatcher.end());
if (position >= Integer.parseInt(splitTriple[1])
&& position <= Integer.parseInt(splitTriple[2])) {
phrase = phrase + " " + word;
}
} // while - wordMatcher
} // while - Line
} catch (IOException ex) {
System.err.println("File " + inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1)
+ " not found. Program terminated.\n");
System.exit(1);
}
detailedWriter.println(splitTriple[0] + "," +
inputFileNames.get(Integer.parseInt(splitTriple[0]) - 1) + "," +
splitTriple[1] + "," +
splitTriple[2] + "," +
phrase.trim());
}
resultWriter.close();
detailedWriter.close();
} else {
System.out.println("No results found from your query.");
}
} else {
System.out.println("No results found from your query.");
}
}
/*
*
* GLOBAL VARIABLES
*
*/
// An array to hold Gutenberg corpus file names
static ArrayList<String> inputFileNames = new ArrayList<String>();
// To keep count of the amount of files in the corpus provided
static int fileCount = 0;
// An array of default output file names for ease of access.
static String outputFiles[] = new String[] {
"proximity_query_result.csv",
"proximity_query_detailed_result.csv",
};
static String outputPath = "";
/*
*
* HELPER METHODS
*
*/
/*
* loads all files names in the directory subtree into an array
* violates good programming practice by accessing a global variable
* (inputFileNames)
*/
public static void listFilesInPath(final File path) {
for (final File fileEntry : path.listFiles()) {
if (fileEntry.isDirectory()) {
listFilesInPath(fileEntry);
} else if (fileEntry.getName().endsWith((".txt"))) {
fileCount++;
inputFileNames.add(fileEntry.getPath());
}
}
}
/*
*
* MAIN METHOD
*
*/
public static void main(String[] args) {
long startTime = System.nanoTime();
int error = 0;
/*
* Did the user provide correct number of command line arguments?
* If not, print message and exit
*/
if (args.length != 5) {
System.err.println("\nNumber of command line arguments must be 5");
System.err.println("You have given " + args.length + " command line arguments");
System.err.println("Incorrect usage. Program terminated");
System.err.println(
"Correct usage: java PositionalIndex <path-to-input-files> <path-to-output-result-files> <first-word> <second-word> <int-distance-between-words>");
error = 1;
}
if (!(args[2] != null && args[2].matches("^[a-zA-Z]*$"))) {
System.err.println("Error: <first-word> argument must only have alphabet letters in the input.");
error = 1;
}
if (!(args[3] != null && args[3].matches("^[a-zA-Z]*$"))) {
System.err.println("Error: <second-word> argument must only have alphabet letters in the input.");
error = 1;
}
if (Integer.parseInt(args[4]) < 1) {
System.err.println("Error: <int-distance-between-words> argument must be greater than 0.");
error = 1;
}
if (error == 1) {
System.exit(1);
}
/*
* If the files exists, we need to empty them.
* We will be appending new data into the documents
*/
for (String file : outputFiles) {
String path = args[1] + "\\" + args[2].toLowerCase() + "_" + args[3].toLowerCase() + "_" + args[4] + "_"
+ file;
try {
new PrintWriter(path, "UTF-8").close();
} catch (FileNotFoundException ex) {
System.err.println(ex);
System.err.println("\nProgram terminated\n");
System.exit(1);
} catch (UnsupportedEncodingException ex) {
System.err.println(ex);
System.err.println("\nProgram terminated\n");
System.exit(1);
}
}
/*
* Extract input file name from command line arguments
* This is the name of the file from the Gutenberg corpus
*/
String inputFileDirName = args[0];
System.out.println("\nInput files directory path name is: " + inputFileDirName);
/*
* Extract output path from command line arguments
* This is the name of the file from the Gutenberg corpus
*/
outputPath = args[1];
System.out.println("Output directory path name is: " + outputPath);
// Collects file names and write them to
listFilesInPath(new File(inputFileDirName));
System.out.println("Number of Gutenberg corpus files: " + fileCount);
// br for efficiently reading characters from an input stream
BufferedReader br = null;
/*
* wordPattern specifies pattern for words using a regular expression
* wordMatcher finds words by spotting word patterns with input
*/
Pattern wordPattern = Pattern.compile("[a-zA-Z]+");
Matcher wordMatcher;
/*
* line - a line read from file
* word - an extracted word from a line
*/
String line, word;
// Initialize new Positional Index
PositionalIndex positionalIndex = new PositionalIndex();
System.out.println("\nBuilding Positional Index...");
// Process one file at a time
for (int index = 0; index < fileCount; index++) {
System.out.println("Processing: " + inputFileNames.get(index));
// Keep track of document position.
int docPosition = 0;
/*
* Keep track of Doc ID for assignment for building the positional
* index data. They start at 1.
*/
int docID = 1 + index;
/*
* Open the input file, read one line at a time, extract words
* in the line, extract characters in a word, write words and
* character counts to disk files
*/
try {
/*
* Get a BufferedReader object, which encapsulates
* access to a (disk) file
*/
br = new BufferedReader(new FileReader(inputFileNames.get(index)));
/*
* As long as we have more lines to process, read a line
* the following line is doing two things: makes an assignment
* and serves as a boolean expression for while test
*/
while ((line = br.readLine()) != null) {
// process the line by extracting words using the wordPattern
wordMatcher = wordPattern.matcher(line);
// Will store a cleaner version of line into String ArrayList
ArrayList<String> cleanLine = new ArrayList<String>();
// Process one word at a time
while (wordMatcher.find()) {
// Extract and convert the word to lowercase
word = line.substring(wordMatcher.start(), wordMatcher.end());
cleanLine.add(word.toLowerCase());
} // while - wordMatcher
/*
* Handles cases if the line is empty
*
* Without this, it will count empty strings
* because cleanLine is originally empty.
*/
if (!cleanLine.isEmpty()) {
for (String term : cleanLine) {
positionalIndex.updatePositionalIndex(term, docID, ++docPosition);
}
}
} // while - Line
} // try
catch (IOException ex) {
System.err.println("File " + inputFileNames.get(index) + " not found. Program terminated.\n");
System.exit(1);
}
} // for -- Process one file at a time
System.out.println("\nPositional Index Built.");
System.out.println("\nNow performing proximity search...");
positionalIndex.proximitySearch(args[2].toLowerCase(), args[3].toLowerCase(), Integer.parseInt(args[4]));
// End Process Timer
long endTime = System.nanoTime();
System.out.println("\nProcess Completed in " +
(double) (endTime - startTime) / 1_000_000_000 + " seconds.\n");
} // main()
} // class