File size: 13,081 Bytes
60be607
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
from modules import shared, utils
from pathlib import Path
import requests
import tqdm
import json

'''
def get_gpu_memory_usage(rank):
    return {
        'total': round(torch.cuda.get_device_properties(rank).total_memory / (1024**3), 2),
        'max': round(torch.cuda.max_memory_allocated(rank) / (1024**3), 2),
        'reserved': round(torch.cuda.memory_reserved(rank) / (1024**3), 2),
        'allocated': round(torch.cuda.memory_allocated(rank) / (1024**3), 2)
    }
'''

def list_subfoldersByTime(directory):

    if not directory.endswith('/'):
        directory += '/'
    subfolders = []
    subfolders.append('None') 
    path = directory
    name_list = os.listdir(path)
    full_list = [os.path.join(path,i) for i in name_list]
    time_sorted_list = sorted(full_list, key=os.path.getmtime,reverse=True)

    for entry in time_sorted_list:
        if os.path.isdir(entry):
            entry_str = f"{entry}"  # Convert entry to a string
            full_path = entry_str
            entry_str = entry_str.replace('\\','/')
            entry_str = entry_str.replace(f"{directory}", "")  # Remove directory part
            subfolders.append(entry_str)

    return subfolders

def get_available_loras_local(_sortedByTime):
    
    model_dir = shared.args.lora_dir  # Update with the appropriate directory path
    subfolders = []
    if _sortedByTime:
        subfolders = list_subfoldersByTime(model_dir)
    else:
        subfolders = utils.get_available_loras()        

    return subfolders


# FPHAM SPLIT BY SENTENCE BLOCK ===============
     
def split_sentences(text: str, cutoff_len: int):
    sentences = []
    sentence = ''
    delimiters = ['. ', '? ', '! ', '... ', '.\n', '?\n', '!\n','...\n','</s>','<//>']
    abbreviations = ['Mr. ', 'Mrs. ', 'Dr. ', 'Ms. ', 'St. ', 'Prof. ', 'Jr. ', 'Ltd. ', 'Capt. ', 'Col. ', 'Gen. ', 'Ave. ', 'Blvd. ', 'Co. ', 'Corp. ', 'Dept. ', 'Est. ', 'Gov. ', 'Inc. ', 'Ph.D. ', 'Univ. ']
    errors = 0
    max_cut = cutoff_len-1
    prev_char = ''  

    for char in text:
        sentence += char

    
        if (any(sentence.endswith(delimiter) for delimiter in delimiters) and
            not (prev_char.isupper() and len(sentence) >= 3 and sentence[-3] != ' ') and 
            not any(sentence.endswith(abbreviation) for abbreviation in abbreviations)):
            tokens = shared.tokenizer.encode(sentence)
            
            if len(tokens) > max_cut:
                tokens = tokens[:max_cut]
                sentence = shared.tokenizer.decode(tokens, skip_special_tokens=True)
                errors = errors + 1

            sentences.append({'text': sentence, 'size': len(tokens)})
            
            sentence = ''

        prev_char = char

    if sentence:
        tokens = shared.tokenizer.encode(sentence)
        if len(tokens) > max_cut:
            tokens = tokens[:max_cut]
            sentence = shared.tokenizer.decode(tokens, skip_special_tokens=True)  
            errors = errors + 1

        sentences.append({'text': sentence, 'size': len(tokens)})

    if errors > 0:
        print(f"Trimmed sentences beyond Cutoff Length: {errors}")

    return sentences

# The goal of following code is to create blocks of text + overlapping blocks while:
# respects sentence boundaries
# always uses all the text 
# hard cut defined by hard_cut_string or </s> will always end at the end of data block
# no overlapping blocks will be created across hard cut or across </s> token

def precise_cut(text: str, overlap: bool, min_chars_cut: int, eos_to_hc: bool, cutoff_len: int, hard_cut_string: str, debug_slicer:bool):

    EOSX_str = '<//>' #hardcut placeholder
    EOS_str = '</s>' 
    print("Precise raw text slicer: ON")
    
    cut_string = hard_cut_string.replace('\\n', '\n')
    text = text.replace(cut_string, EOSX_str)
    sentences = split_sentences(text, cutoff_len)

    print(f"Sentences: {len(sentences)}")
    sentencelist = []
    currentSentence = ''
    totalLength = 0
    max_cut = cutoff_len-1
    half_cut = cutoff_len//2
    halfcut_length = 0

    edgeindex = []
    half_index = 0

    for index, item in enumerate(sentences):
        
        if halfcut_length+ item['size'] < half_cut:
            halfcut_length += item['size']
            half_index = index
        else:
            edgeindex.append(half_index)
            halfcut_length = -2 * max_cut


        if totalLength + item['size'] < max_cut and not currentSentence.endswith(EOSX_str): 
            currentSentence += item['text']
            totalLength += item['size']
        else:

            if len(currentSentence.strip()) > min_chars_cut:
                sentencelist.append(currentSentence.strip())

            currentSentence = item['text']
            totalLength = item['size']
            halfcut_length = item['size']
            
    if len(currentSentence.strip()) > min_chars_cut:    
        sentencelist.append(currentSentence.strip())

    unique_blocks = len(sentencelist)
    print(f"Text Blocks: {unique_blocks}")

    #overlap strategies: 
    # don't overlap across HARD CUT (EOSX)
    if overlap:
        for edge_idx in edgeindex:
            currentSentence = ''
            totalLength = 0

            for item in sentences[edge_idx:]:
                if totalLength + item['size'] < max_cut:
                    currentSentence += item['text']
                    totalLength += item['size']
                else:
                    #if by chance EOSX is at the end then it's acceptable
                    if currentSentence.endswith(EOSX_str) and len(currentSentence.strip()) > min_chars_cut:
                            sentencelist.append(currentSentence.strip())    
                    # otherwise don't cross hard cut    
                    elif EOSX_str not in currentSentence and len(currentSentence.strip()) > min_chars_cut:
                        sentencelist.append(currentSentence.strip())
                    
                    currentSentence = ''
                    totalLength = 0
                    break
        
        print(f"+ Overlapping blocks: {len(sentencelist)-unique_blocks}")

    num_EOS = 0
    for i in range(len(sentencelist)):
        if eos_to_hc:
            sentencelist[i] = sentencelist[i].replace(EOSX_str, EOS_str)
        else:
            sentencelist[i] = sentencelist[i].replace(EOSX_str, '')
        
        #someone may have had stop strings in the raw text...
        sentencelist[i] = sentencelist[i].replace("</s></s>", EOS_str)
        num_EOS += sentencelist[i].count(EOS_str)

    if num_EOS > 0:
        print(f"+ EOS count: {num_EOS}")

    #final check for useless lines
    sentencelist = [item for item in sentencelist if item.strip() != "</s>"]
    sentencelist = [item for item in sentencelist if item.strip() != ""]


    if debug_slicer:
                    # Write the log file
        Path('logs').mkdir(exist_ok=True)
        sentencelist_dict = {index: sentence for index, sentence in enumerate(sentencelist)}
        output_file = "logs/sentencelist.json"
        with open(output_file, 'w') as f:
            json.dump(sentencelist_dict, f,indent=2)
        
        print("Saved sentencelist.json in logs folder")
    
    return sentencelist   


def sliding_block_cut(text: str, min_chars_cut: int, eos_to_hc: bool, cutoff_len: int, hard_cut_string: str, debug_slicer:bool):

    EOSX_str = '<//>' #hardcut placeholder
    EOS_str = '</s>' 
    print("Mega Block Overlap: ON")
    
    cut_string = hard_cut_string.replace('\\n', '\n')
    text = text.replace(cut_string, EOSX_str)
    sentences = split_sentences(text, cutoff_len)

    print(f"Sentences: {len(sentences)}")
    sentencelist = []
    
    max_cut = cutoff_len-1

    #print(f"max_cut: {max_cut}")
    advancing_to = 0

    prev_block_lastsentence = ""
    

    for i in range(len(sentences)):
        totalLength = 0
        currentSentence = ''
        lastsentence = ""
        
        if i >= advancing_to:
            for k in range(i, len(sentences)):
                
                current_length = sentences[k]['size']

                if totalLength + current_length <= max_cut and not currentSentence.endswith(EOSX_str):
                    currentSentence += sentences[k]['text']
                    totalLength += current_length
                    lastsentence = sentences[k]['text']
                else:
                    if len(currentSentence.strip()) > min_chars_cut:
                        if prev_block_lastsentence!=lastsentence:
                            sentencelist.append(currentSentence.strip())
                            prev_block_lastsentence = lastsentence
                        
                    advancing_to = 0
                    if currentSentence.endswith(EOSX_str):
                        advancing_to = k

                    currentSentence = ""
                    totalLength = 0
                    break
            
            if currentSentence != "":
                if len(currentSentence.strip()) > min_chars_cut:
                    sentencelist.append(currentSentence.strip())

    unique_blocks = len(sentencelist)
    print(f"Text Blocks: {unique_blocks}")
    num_EOS = 0
    for i in range(len(sentencelist)):
        if eos_to_hc:
            sentencelist[i] = sentencelist[i].replace(EOSX_str, EOS_str)
        else:
            sentencelist[i] = sentencelist[i].replace(EOSX_str, '')
        
        #someone may have had stop strings in the raw text...
        sentencelist[i] = sentencelist[i].replace("</s></s>", EOS_str)
        num_EOS += sentencelist[i].count(EOS_str)

    if num_EOS > 0:
        print(f"+ EOS count: {num_EOS}")

    #final check for useless lines
    sentencelist = [item for item in sentencelist if item.strip() != "</s>"]
    sentencelist = [item for item in sentencelist if item.strip() != ""]


    if debug_slicer:
                    # Write the log file
        Path('logs').mkdir(exist_ok=True)
        sentencelist_dict = {index: sentence for index, sentence in enumerate(sentencelist)}
        output_file = "logs/sentencelist.json"
        with open(output_file, 'w') as f:
            json.dump(sentencelist_dict, f,indent=2)
        
        print("Saved sentencelist.json in logs folder")
    
    return sentencelist   

# Example usage:
# download_file_from_url('https://example.com/path/to/your/file.ext', '/output/directory')

def download_file_from_url(url, overwrite, output_dir_in, valid_extensions = {'.txt', '.json'}):
    try:
    # Validate and sanitize the URL
    #parsed_url = urllib.parse.urlparse(url)
    #if not parsed_url.netloc:
    #    raise ValueError("Invalid URL")
    #filename = os.path.basename(parsed_url.path)

    # Get the filename from the URL

        session = requests.Session()
        headers = {}
        mode = 'wb'
        filename = url.split('/')[-1]

        output_dir = str(output_dir_in)
        # Construct the full path to the output file
        local_filename = os.path.join(output_dir, filename)

        # Check if the local file already exists
        overw = ''
        if os.path.exists(local_filename):
            if not overwrite:
                yield f"File '{local_filename}' already exists. Aborting."
                return
            else:
                overw = ' [Overwrite existing]'

        filename_lower = filename.lower()

        # Send an HTTP GET request to the URL with a timeout
        file_extension = os.path.splitext(filename_lower)[-1]
        
        if file_extension not in valid_extensions:
            yield f"Invalid file extension: {file_extension}. Only {valid_extensions} files are supported."
            return

        with session.get(url, stream=True, headers=headers, timeout=10) as r:
            r.raise_for_status() 
            # total size can be wildly inaccurate
            #total_size = int(r.headers.get('content-length', 0))
            
            block_size = 1024 * 4  
            with open(local_filename, mode) as f:
                count = 0
                for data in r.iter_content(block_size):
                    f.write(data)
                    count += len(data)

                    yield f"Downloaded: {count} " + overw

            # Verify file size if possible
            if os.path.exists(local_filename):
                downloaded_size = os.path.getsize(local_filename)
                if downloaded_size > 0:
                    yield f"File '{filename}' downloaded to '{output_dir}' ({downloaded_size} bytes)."
                    print("File Downloaded")
                else:
                    print("Downloaded file is zero")
                    yield f"Failed. Downloaded file size is zero)."
            else:
                print(f"Error: {local_filename} failed to download.")
                yield f"Error: {local_filename} failed to download"

    except Exception as e:
        print(f"An error occurred: {e}")
        yield f"An error occurred: {e}"

    finally:
        # Close the session to release resources
        session.close()