aboutsummaryrefslogtreecommitdiffstats
path: root/devourer.py
blob: 8532bf32b857fd3f8af5e77d008f3b8c8f19753e (plain) (blame)
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
# _*_ coding=utf-8 _*_

import logging
import tika
import nltk
import random
import string
import os
from newspaper import Article, build, Config
from bs4 import BeautifulSoup
from contextlib import closing
from requests import get, Response
from requests.exceptions import RequestException
from re import findall
from readability import Document
from gtts import gTTS
from datetime import datetime as time
from fastapi import FastAPI


# FIXME-maybe actually really do some logging
def logError(err: RequestException) -> None:
    """Logs the errors."""
    logging.exception(err)


def isAGoodResponse(resp: Response) -> bool:
    """Checks whether the get we sent got a 200 response."""
    content_type = resp.headers["Content-Type"].lower()
    return resp.status_code == 200 and content_type is not None


def simpleGet(url: str) -> bytes:
    """Issues a simple get request."""
    try:
        with closing(get(url, stream=True)) as resp:
            if isAGoodResponse(resp):
                return resp.content
            else:
                return None
    except RequestException as e:
        logError("Error during requests to {0} : {1}".format(url, str(e)))
        return None


def getWithParams(url: str, params: dict) -> dict:
    """Issues a get request with params."""
    try:
        with closing(get(url, params=params, stream=True)) as resp:
            if isAGoodResponse(resp):
                return resp.json()
            else:
                return None
    except RequestException as e:
        logError("Error during requests to {0} : {1}".format(url, str(e)))
        return None


def getRandStr(n):
    """Return a random string of the given length."""
    return "".join([random.choice(string.lowercase) for i in range(n)])


def getURLS(source: str) -> dict:
    """Extracts the urls from a website."""
    result = dict()
    raw_ml = simpleGet(source)
    ml = BeautifulSoup(raw_ml, "lxml")

    rand_tmp = "/tmp/" + getRandStr(20)
    ml_str = repr(ml)
    tmp = open(rand_tmp, "w")
    tmp.write(ml_str)
    tmp.close()
    tmp = open(rand_tmp, "r")
    url_list = []
    for line in tmp:
        url = findall(
            "http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*(),]|"
            r"(?:%[0-9a-fA-F][0-9a-fA-F]))+",
            line,
        )
        url_list += url
    for elem in url_list:
        result[elem] = elem
    tmp.close()
    return result


def configNews(config: Config) -> None:
    """Configures newspaper."""
    config.fetch_images = False
    config.keep_article_html = True
    config.memoize_articles = False
    config.browser_user_agent = "Chrome/91.0.4464.5"


# FIXME-have to decide whether to use files or urls
def pdfToVoice() -> str:
    """Main function for converting a pdf to an mp3."""
    outfile = str()
    try:
        rawText = tika.parser.from_file()
        tts = gTTS(rawText["content"])
        outfile = getRandStr(20) + ".mp3"
        tts.save(outfile)
    except Exception as e:
        logging.exception(e)
    finally:
        return outfile


def extractRequirements(textBody: str) -> list:
    """Extract the sentences containing the keywords that denote a requirement.

    the keywords are baed on ISO/IEC directives, part 2:
    https://www.iso.org/sites/directives/current/part2/index.xhtml
    """
    result = []
    REQ_KEYWORDS = [
        "shall",
        "shall not",
        "should",
        "should not",
        "must",
        "may",
        "can",
        "cannot",
    ]
    sentences = nltk.sent_tokenize(textBody)
    for sentence in sentences:
        for keyword in REQ_KEYWORDS:
            if sentence.find(keyword) >= 0:
                result.append(sentence)
    return result


def summarizeText(text: str) -> str:
    """Summarize the given text using bart."""
    import transformers

    model = transformers.BartForConditionalGeneration.from_pretrained(
        "facebook/bart-large-cnn"
    )
    tokenizer = transformers.BartTokenizer.from_pretrained(
        "facebook/bart-large-cnn"
    )
    inputs = tokenizer([text], max_length=1024, return_tensors="pt")
    summary_ids = model.generate(
        inputs["input_ids"], num_beams=4, max_length=5, early_stopping=True
    )
    return [
        tokenizer.decode(
            g, skip_special_tokens=True, clean_up_tokenization_spaces=False
        )
        for g in summary_ids
    ]


def textToAudio(text: str) -> str:
    """Transform the given text into audio."""
    path = str()
    try:
        time_str = time.today().strftime("%b-%d-%Y-%M-%S-%f")
        tts = gTTS(text)
        tts.save(os.environ["AUDIO_DUMP_DIR"] + "/" + time_str + ".mp3")
        path = os.environ["AUDIO_DUMP_DIR"] + "/" + time_str + ".mp3"
    except Exception as e:
        logging.exception(e)
    finally:
        return path


def getRequirements(url: str, sourcetype: str) -> list:
    """Runs the single-link main function."""
    result = str()
    results = list()
    try:
        if sourcetype == "html":
            parser = build(url)
            for article in parser.articles:
                a = Article(article.url)
                a.download()
                a.parse()
                doc = Document(a.html)
                # print(doc.summary())
                results = extractRequirements(doc.summary())
        elif sourcetype == "text":
            bytesText = simpleGet(url)
            results = extractRequirements(bytesText.decode("utf-8"))
    except Exception as e:
        logging.exception(e)
    finally:
        result = "".join(results + "\n")
        return result


# FIXME-summary=bart doesnt work
def summarizeLinkToAudio(url, summary) -> str:
    """Summarizes the text inside a given url into audio."""
    result = str()
    try:
        article = Article(url)
        article.download()
        article.parse()
        if summary == "newspaper":
            article.nlp()
            result = article.summary
        elif summary == "none":
            result = article.text
        elif summary == "bart":
            result = article.text
        else:
            print("invalid option for summary type.")
    except Exception as e:
        logging.exception(e)
    finally:
        return result


# FIXME-change my name
def summarizeLinksToAudio(url, summary) -> None:
    """Summarize a list of urls into audio files."""
    results = list()
    result = str()
    try:
        config = Config()
        configNews(config)
        urls = getURLS(url, summary)
        for url in urls:
            results.append(summarizeLinkToAudio(url))
    except Exception as e:
        logging.exception(e)
    finally:
        result = "".join(results)
        return result


def searchWikipedia(search_term: str) -> str:
    """Search wikipedia for a string and return the url.

    reference: https://www.mediawiki.org/wiki/API:Opensearch
    """
    result = str()
    try:
        searchParmas = {
            "action": "opensearch",
            "namespace": "0",
            "search": search_term,
            "limit": "10",
            "format": "json",
        }
        res = getWithParams(os.environ["WIKI_SEARCH_URL"], searchParmas)
        # FIXME-handle wiki redirects/disambiguations
        source = res[3][0]
        result = summarizeLinkToAudio(source, "none")
    except Exception as e:
        logging.exception(e)
    finally:
        return result


def getAudioFromFile(audio_path: str) -> str:
    """Returns the contents of a file in binary format"""
    with open(audio_path, "rb") as audio:
        return audio.read()


app = FastAPI()
nltk.download("punkt")


@app.get("/mila/tika")
async def pdf_to_audio_ep(url: str):
    """turns a pdf into an audiofile"""
    audio_path = pdfToVoice()
    return {
        "Content-Type": "application/json",
        "isOK": True if audio_path != "" else False,
        "audio": getAudioFromFile(audio_path) if audio_path != "" else "",
    }


@app.get("/mila/reqs")
async def extract_reqs_ep(url: str, sourcetype: str = "html"):
    """extracts the requirements from a given url"""
    result = getRequirements()
    return {
        "Content-Type": "application/json",
        "isOK": True if result != "" else False,
        "reqs": result,
    }


@app.get("/mila/wiki")
async def wiki_search_ep(term: str, audio: bool = False):
    """search and summarizes from wikipedia"""
    text = searchWikipedia(term)
    if audio:
        audio_path = textToAudio(text)
        return {
            "Content-Type": "application/json",
            "isOK": (True if audio_path != "" else False)
            and (True if text != "" else False),
            "audio": getAudioFromFile(audio_path) if audio_path != "" else "",
            "text": text,
        }
    else:
        return {
            "Content-Type": "application/json",
            "isOK": True if text != "" else False,
            "audio": "",
            "text": text,
        }


@app.get("/mila/summ")
async def summarize_ep(url: str, summary: str = "none", audio: bool = False):
    """summarize and turn the summary into audio"""
    text = summarizeLinkToAudio(url, summary)
    if audio:
        audio_path = textToAudio(text)
        print(audio_path)
        return {
            "Content-Type": "audio/mpeg",
            # "isOK": (True if audio_path != "" else False)
            # and (True if text != "" else False),
            "audio": getAudioFromFile(audio_path) if audio_path != "" else "",
            # "text": text,
        }
    else:
        return {
            "Content-Type": "application/json",
            "isOK": True if text != "" else False,
            # "audio": "",
            "text": text,
        }


@app.get("/mila/mila")
async def mila_ep(url: str, summary: str = "newspaper", audio: bool = False):
    """extract all the urls and then summarize and turn into audio"""
    text = summarizeLinksToAudio(url, summary)
    if audio:
        audio_path = textToAudio(text)
        print(audio_path)
        return {
            "Content-Type": "application/json",
            "isOK": (True if audio_path != "" else False)
            and (True if text != "" else False),
            "audio": getAudioFromFile(audio_path) if audio_path != "" else "",
            "text": text,
        }
    else:
        return {
            "Content-Type": "application/json",
            "isOK": True if text != "" else False,
            "audio": "",
            "text": text,
        }


@app.get("/mila/health")
async def health_ep():
    return {"isOK": True}


@app.get("/mila/robots.txt")
async def robots_ep():
    return {
        "Content-Type": "apllication/json",
        "User-Agents": "*",
        "Disallow": "/",
    }