io4it 3.0.2.2__tar.gz → 3.0.3.1__tar.gz

{io4it-3.0.2.2 → io4it-3.0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: io4it
-Version: 3.0.2.2
+Version: 3.0.3.1
 Home-page: 
 Author: 
 Author-email: 

{io4it-3.0.2.2 → io4it-3.0.3.1}/io4it.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: io4it
-Version: 3.0.2.2
+Version: 3.0.3.1
 Home-page: 
 Author: 
 Author-email: 

{io4it-3.0.2.2 → io4it-3.0.3.1}/io4it.egg-info/SOURCES.txt

@@ -39,7 +39,6 @@ orangecontrib/IO4IT/widgets/OWmailLoader.py
 orangecontrib/IO4IT/widgets/OWmailSender.py
 orangecontrib/IO4IT/widgets/OWwordpdf2docx.py
 orangecontrib/IO4IT/widgets/__init__.py
-orangecontrib/IO4IT/widgets/../utils/config.json
 orangecontrib/IO4IT/widgets/designer/__init__.py
 orangecontrib/IO4IT/widgets/designer/nogui.ui
 orangecontrib/IO4IT/widgets/designer/ow_file_ext_selector.ui

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWExportMarkdown.py

@@ -27,7 +27,7 @@ else:
 
 class OWExportMarkdown(widget.OWWidget):
     name = "OWExportMarkdown"
-    description = "Auto-exporte content→(docx,pptx,pdf) au même path (base + extensions)."
+    description = "Automatically export content to DOCX, PPTX, and PDF using the same base path."
     icon = "icons/export_md.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
         icon = "icons_dev/export_md.png"

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWExtractTablesDocxToXlsx.py

@@ -23,7 +23,7 @@ class OWExtractTablesDocxToXlsx(widget.OWWidget):
     en fichiers XLSX distincts (une table Word = un fichier XLSX).
     """
     name = "Docx to XLSX"
-    description = "Extrait les tables de documents Word et les sauvegarde en XLSX, avec une option de division (split)."
+    description = "Extract tables from Word documents and save them as XLSX, with an optional split feature."
     category = "AAIT - TOOLBOX"
     icon = "icons/extract_table.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWMarkdownLoader.py

@@ -17,7 +17,7 @@ except ImportError:
 
 class OWMarkdownLoader(widget.OWWidget):
     name = "Markdown Loader"
-    description = "Charge tous les fichiers Markdown d’un dossier (récursif)"
+    description = "Load all Markdown files from a folder (recursively)."
     icon = "icons/load_md.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
         icon = "icons_dev/load_md.png"

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWMarkdownizer.py

@@ -518,7 +518,7 @@ class MarkdownConversionThread(QThread):
 
 class FileProcessorApp(widget.OWWidget):
     name = "Markdownizer"
-    description = "Convert PDFs, DOCX, PPTX to Markdown (texte seul & word only)"
+    description = "[deprecated]Convert PDFs, DOCX, PPTX to Markdown (ignore image)"
     icon = "icons/dep_md_old.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
        icon = "icons_dev/dep_md_old.png"

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWParserHTML.py

@@ -7,6 +7,7 @@ import asyncio
 import aiohttp
 import html2text
 from bs4 import BeautifulSoup
+import urllib.request
 
 if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
     from Orange.widgets.orangecontrib.AAIT.utils import thread_management
@@ -112,13 +113,16 @@ class ParseHMTL(OWWidget):
                 'Connection': 'keep-alive',
                 'Upgrade-Insecure-Requests': '1'
         }
-        async with session.get(url, headers=headers) as response:
+        proxies = urllib.request.getproxies()
+        if "http" in proxies:
+            proxies = proxies["http"]
+        else:
+            proxies = None
+        async with session.get(url, headers=headers, proxy=proxies) as response:
             if response.status != 200:
                 raise Exception(f"HTTP {response.status}")
-
             html = await response.text()
         soup = BeautifulSoup(html, 'html.parser')
-
         meta_desc = ''
         meta_tag = soup.find('meta', attrs={'name': 'description'})
         if not meta_tag:

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWS3Uploader.py

@@ -9,7 +9,7 @@ from Orange.data import Table
 
 class OWS3FileDownloader(OWWidget):
     name = "S3 File Uploader"
-    description = "Envoies les fichiers listés depuis un répertoire local vers s3."
+    description = "Upload the listed files from a local directory to S3."
     icon = "icons/upload.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
         icon = "icons_dev/upload.png"

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWS3downloader.py

@@ -8,7 +8,7 @@ from Orange.data import Table
 
 class OWS3FileDownloader(OWWidget):
     name = "S3 File Downloader"
-    description = "Télécharge les fichiers listés depuis S3 vers un répertoire local."
+    description = "Download the listed files from S3 to a local directory."
     icon = "icons/download.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
         icon = "icons_dev/download.png"

{io4it-3.0.2.2 → io4it-3.0.3.1}/orangecontrib/IO4IT/widgets/OWS3list.py

@@ -8,7 +8,7 @@ import os
 
 class OWS3FileLister(OWWidget):
     name = "S3 File Lister"
-    description = "Liste les fichiers d'un bucket S3 et affiche leurs détails."
+    description = "List the files in an S3 bucket and display their details."
     icon = "icons/list_aws.png"
     if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
         icon = "icons_dev/list_aws.png"

io4it-3.0.3.1/orangecontrib/IO4IT/widgets/OWWebSearch.py

@@ -0,0 +1,307 @@
+import os
+import sys
+import Orange
+from Orange.widgets.widget import Input, Output
+from AnyQt.QtWidgets import QApplication, QPushButton
+from Orange.widgets.settings import Setting
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import quote, urlparse, urljoin, parse_qs
+import unicodedata
+import re
+
+if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
+    from Orange.widgets.orangecontrib.AAIT.utils import thread_management, base_widget
+    from Orange.widgets.orangecontrib.HLIT_dev.remote_server_smb import convert
+else:
+    from orangecontrib.AAIT.utils import thread_management, base_widget
+    from orangecontrib.HLIT_dev.remote_server_smb import convert
+
+class WebSearch(base_widget.BaseListWidget):
+    name = "WebSearch"
+    description = "Search url website from a query with DDG."
+    icon = "icons/websearch.png"
+    if "site-packages/Orange/widgets" in os.path.dirname(os.path.abspath(__file__)).replace("\\", "/"):
+        icon = "icons_dev/websearch.png"
+    priority = 3000
+    gui = ""
+    want_control_area = False
+    category = "AAIT - TOOLBOX"
+    gui = os.path.join(os.path.dirname(os.path.abspath(__file__)), "designer/owwebsearch.ui")
+    # Settings
+    selected_column_name = Setting("content")
+
+    class Inputs:
+        data = Input("Data", Orange.data.Table)
+
+    @Inputs.data
+    def set_data(self, in_data):
+        self.data = in_data
+        if in_data is None:
+            self.Outputs.data.send(None)
+            return
+        if self.data:
+            self.var_selector.add_variables(self.data.domain)
+            self.var_selector.select_variable_by_name(self.selected_column_name)
+        self.run()
+
+    class Outputs:
+        data = Output("Data", Orange.data.Table)
+
+
+    def __init__(self):
+        super().__init__()
+        # Qt Management
+        self.setFixedWidth(480)
+        self.setFixedHeight(450)
+
+        self.pushButton_run =self.findChild(QPushButton, 'pushButton_send')
+        self.pushButton_run.clicked.connect(self.run)
+
+
+    def normaliser_texte(self, txt: str) -> str:
+        """
+        Met en minuscules, retire les accents et trim.
+        """
+        if not txt:
+            return ""
+        txt = txt.lower()
+        txt = unicodedata.normalize("NFD", txt)
+        txt = "".join(c for c in txt if not unicodedata.combining(c))
+        return txt.strip()
+
+    def extraire_mots_cles(self, requete: str):
+        """
+        Découpe la requête en mots-clés simples, en retirant
+        les mots très fréquents (du, de, le, la, etc.).
+        """
+        stopwords = {"du", "de", "des", "le", "la", "les", "un", "une", "au", "aux", "et", "en", "pour", "sur", "a"}
+        req_norm = self.normaliser_texte(requete)
+        mots = re.findall(r"\w+", req_norm)
+        mots_cles = [m for m in mots if m not in stopwords and len(m) > 2]
+        return mots_cles or mots
+
+    def recherche_duckduckgo(self, query, max_results=10):
+        q = quote(query)
+        url = f"https://duckduckgo.com/html/?q={q}"
+        headers = {"User-Agent": "Mozilla/5.0"}
+
+        try:
+            r = requests.get(url, headers=headers, timeout=10)
+            r.raise_for_status()
+        except requests.RequestException as e:
+            print(f"[ERREUR] Problème lors de la requête DuckDuckGo : {e}")
+            return []
+
+        soup = BeautifulSoup(r.text, "html.parser")
+        resultats = []
+
+        for a in soup.select("a.result__a")[:max_results]:
+            titre = a.get_text(strip=True)
+            lien = a.get("href", "")
+
+            # Gestion des liens de redirection DuckDuckGo
+            parsed = urlparse(lien)
+            if parsed.netloc and "duckduckgo.com" in parsed.netloc and parsed.path.startswith("/l/"):
+                qs = parse_qs(parsed.query)
+                if "uddg" in qs:
+                    lien = qs["uddg"][0]
+
+            # Lien relatif -> absolu
+            if lien.startswith("/"):
+                lien = urljoin("https://duckduckgo.com", lien)
+
+            resultats.append((titre, lien))
+
+        return resultats
+
+    def extraire_domaines(self, resultats_search):
+        domaines = set()
+        for _titre, url in resultats_search:
+            try:
+                parsed = urlparse(url)
+                scheme = parsed.scheme or "https"
+                if not parsed.netloc:
+                    continue
+                domaine = f"{scheme}://{parsed.netloc}"
+                domaines.add(domaine)
+            except Exception:
+                pass
+        return list(domaines)
+
+    def trouver_flux_rss(self, url_site):
+        try:
+            r = requests.get(url_site, headers={"User-Agent": "Mozilla/5.0"}, timeout=10)
+            r.raise_for_status()
+        except requests.RequestException as e:
+            print(f"[ERREUR] Impossible d'accéder à {url_site} : {e}")
+            return []
+
+        soup = BeautifulSoup(r.text, "html.parser")
+        flux = []
+
+        for link in soup.find_all("link", type="application/rss+xml"):
+            href = link.get("href")
+            if href:
+                href = urljoin(url_site, href)
+                flux.append(href)
+
+        for link in soup.find_all("a"):
+            href = link.get("href", "")
+            if not href:
+                continue
+            href_norm = href.lower()
+            if "rss" in href_norm or "feed" in href_norm:
+                flux.append(urljoin(url_site, href))
+
+        return list(set(flux))
+
+    def rechercher_articles_dans_flux(self, requete, flux_list, max_results=20):
+        mots_cles = self.extraire_mots_cles(requete)
+        articles = []
+
+        headers = {"User-Agent": "Mozilla/5.0"}
+
+        for flux in flux_list:
+            try:
+                r = requests.get(flux, headers=headers, timeout=10)
+                r.raise_for_status()
+                # Parse du flux en XML
+                soup = BeautifulSoup(r.content, "xml")
+            except requests.RequestException as e:
+                print(f"[ERREUR] Problème lors de la lecture du flux {flux} : {e}")
+                continue
+
+            # Gestion RSS (<item>) et Atom (<entry>)
+            for entry in soup.find_all(["item", "entry"]):
+                # Titre
+                titre_tag = entry.find("title")
+                titre = titre_tag.get_text(strip=True) if titre_tag else ""
+
+                # Résumé / description
+                resume_tag = entry.find("description") or entry.find("summary")
+                resume = resume_tag.get_text(strip=True) if resume_tag else ""
+
+                # Lien
+                lien_tag = entry.find("link")
+                lien = ""
+                if lien_tag:
+                    # Atom : <link href="...">
+                    if lien_tag.has_attr("href"):
+                        lien = lien_tag["href"]
+                    else:
+                        # RSS : <link>https://...</link>
+                        lien = lien_tag.get_text(strip=True)
+
+                # Date
+                date_tag = (
+                        entry.find("pubDate")
+                        or entry.find("published")
+                        or entry.find("updated")
+                )
+                date = date_tag.get_text(strip=True) if date_tag else "Date inconnue"
+
+                texte_complet = self.normaliser_texte(titre + " " + resume)
+
+                # Condition : au moins un mot-clé présent dans titre+résumé
+                if any(mot in texte_complet for mot in mots_cles):
+                    articles.append(
+                        {
+                            "titre": titre,
+                            "url": lien,
+                            "date": date,
+                            "source_flux": flux,
+                        }
+                    )
+                    if len(articles) >= max_results:
+                        return articles
+
+        return articles
+
+    def pipeline_veille_requete(self,requete):
+        resultats = self.recherche_duckduckgo(requete)
+        if not resultats:
+            print("Aucun résultat trouvé sur DuckDuckGo.")
+            return []
+        print(resultats)
+        domaines = self.extraire_domaines(resultats)
+
+        flux = []
+        for d in domaines:
+            found = self.trouver_flux_rss(d)
+            if found:
+                print(f"Flux trouvés sur {d}:")
+                for f in found:
+                    print(" ->", f)
+                flux.extend(found)
+
+        flux = list(set(flux))
+
+        if not flux:
+            return [
+                {"titre": t, "url": u, "date": None, "source_flux": None, "source": "web"}
+                for t, u in resultats
+            ]
+        articles = self.rechercher_articles_dans_flux(requete, flux)
+
+        if not articles:
+            return [
+                {"titre": t, "url": u, "date": None, "source_flux": None, "source": "web"}
+                for t, u in resultats
+            ]
+        return articles
+
+
+    def run(self):
+        self.error("")
+        self.warning("")
+        if self.data is None:
+            self.Outputs.data.send(None)
+            return
+
+        if not self.selected_column_name in self.data.domain:
+            self.warning(f'Previously selected column "{self.selected_column_name}" does not exist in your data.')
+            return
+
+        self.query = self.data.get_column(self.selected_column_name)[0]
+
+        self.progressBarInit()
+        self.thread = thread_management.Thread(self.pipeline_veille_requete, self.query)
+        self.thread.progress.connect(self.handle_progress)
+        self.thread.result.connect(self.handle_result)
+        self.thread.finish.connect(self.handle_finish)
+        self.thread.start()
+
+    def handle_progress(self, progress) -> None:
+        value = progress[0]
+        text = progress[1]
+        if value is not None:
+            self.progressBarSet(value)
+        if text is None:
+            self.textBrowser.setText("")
+        else:
+            self.textBrowser.insertPlainText(text)
+
+    def handle_result(self, result):
+        if result is None or len(result) == 0:
+            self.Outputs.data.send(None)
+            return
+        data = convert.convert_json_implicite_to_data_table(result)
+        self.Outputs.data.send(data)
+
+    def handle_finish(self):
+        self.progressBarFinished()
+
+    def post_initialized(self):
+        pass
+
+
+if __name__ == "__main__":
+    app = QApplication(sys.argv)
+    my_widget = WebSearch()
+    my_widget.show()
+
+    if hasattr(app, "exec"):
+        sys.exit(app.exec())
+    else:
+        sys.exit(app.exec_())

io4it-3.0.3.1/orangecontrib/IO4IT/widgets/designer/owwebsearch.ui

@@ -0,0 +1,131 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>Form</class>
+ <widget class="QWidget" name="Form">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>477</width>
+    <height>409</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Form</string>
+  </property>
+  <widget class="QGroupBox" name="groupBox">
+   <property name="geometry">
+    <rect>
+     <x>20</x>
+     <y>40</y>
+     <width>431</width>
+     <height>71</height>
+    </rect>
+   </property>
+   <property name="title">
+    <string>Explanation</string>
+   </property>
+   <widget class="QLabel" name="Description">
+    <property name="geometry">
+     <rect>
+      <x>10</x>
+      <y>10</y>
+      <width>411</width>
+      <height>51</height>
+     </rect>
+    </property>
+    <property name="text">
+     <string>This widget takes a query input and return a list of web site related to it .</string>
+    </property>
+    <property name="textFormat">
+     <enum>Qt::AutoText</enum>
+    </property>
+    <property name="alignment">
+     <set>Qt::AlignLeading|Qt::AlignLeft|Qt::AlignVCenter</set>
+    </property>
+    <property name="wordWrap">
+     <bool>true</bool>
+    </property>
+   </widget>
+  </widget>
+  <widget class="QPushButton" name="pushButton_send">
+   <property name="enabled">
+    <bool>true</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>149</x>
+     <y>344</y>
+     <width>301</width>
+     <height>31</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>Run</string>
+   </property>
+  </widget>
+  <widget class="QCheckBox" name="checkBox_send">
+   <property name="enabled">
+    <bool>false</bool>
+   </property>
+   <property name="geometry">
+    <rect>
+     <x>20</x>
+     <y>350</y>
+     <width>131</width>
+     <height>16</height>
+    </rect>
+   </property>
+   <property name="text">
+    <string>Auto send data</string>
+   </property>
+  </widget>
+  <widget class="QGroupBox" name="groupBox_3">
+   <property name="geometry">
+    <rect>
+     <x>20</x>
+     <y>150</y>
+     <width>431</width>
+     <height>161</height>
+    </rect>
+   </property>
+   <property name="title">
+    <string>Column selection</string>
+   </property>
+   <widget class="QLabel" name="Description_4">
+    <property name="geometry">
+     <rect>
+      <x>10</x>
+      <y>30</y>
+      <width>411</width>
+      <height>61</height>
+     </rect>
+    </property>
+    <property name="text">
+     <string/>
+    </property>
+    <property name="textFormat">
+     <enum>Qt::AutoText</enum>
+    </property>
+    <property name="alignment">
+     <set>Qt::AlignLeading|Qt::AlignLeft|Qt::AlignVCenter</set>
+    </property>
+    <property name="wordWrap">
+     <bool>true</bool>
+    </property>
+   </widget>
+   <widget class="QWidget" name="placeholder" native="true">
+    <property name="geometry">
+     <rect>
+      <x>0</x>
+      <y>20</y>
+      <width>431</width>
+      <height>141</height>
+     </rect>
+    </property>
+   </widget>
+  </widget>
+ </widget>
+ <resources/>
+ <connections/>
+</ui>

{io4it-3.0.2.2 → io4it-3.0.3.1}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 # Configuration
 NAME = "io4it"
-VERSION = "3.0.2.2"
+VERSION = "3.0.3.1"
 
 INSTALL_REQUIRES = [
     "torchvision==0.23.0",

io4it-3.0.2.2/orangecontrib/IO4IT/utils/config.json

@@ -1,45 +0,0 @@
-{
-  "domain_context": {
-    "prix": ["cours", "cotation", "tarif", "valeur", "coût"],
-    "marché": ["négoce", "commerce", "trading", "bourse", "mondial", "international"],
-    "économie": ["économique", "fiscal", "finance", "budget"],
-    "bourse": ["action", "indice", "trading", "investissement"],
-
-    "porc": ["porcin", "viande porcine", "cochon", "élevage"],
-    "agriculture": ["agricole", "exploitation", "récolte", "production"],
-    "élevage": ["bétail", "ferme", "cheptel"],
-
-    "produits mer": ["coquillage", "crustacé", "mollusque", "pêche", "aquaculture"],
-    "saint jacques": ["coquille", "pectinidé", "noix", "scallop"],
-    "coquille": ["bivalve", "mollusque", "pêche"],
-
-    "actualités": ["news", "information", "récent", "nouveau"],
-    "tendances": ["évolution", "dynamique", "orientation", "conjoncture"],
-    "perspectives": ["prévisions", "anticipations", "outlook", "horizon"],
-    "conjoncture": ["situation", "contexte", "analyse", "bilan"],
-
-    "scientifique": ["espèce", "taxonomie", "biologie", "distribution", "habitat"],
-    "pêche": ["fishery", "capture", "exploitation", "stock"],
-
-    "ia": ["intelligence artificielle", "machine learning", "deep learning"],
-    "technologie": ["tech", "digital", "numérique", "innovation"],
-    "logiciel": ["software", "application", "programme"],
-
-    "article": ["publication", "presse", "média", "journal"],
-    "recherche": ["étude", "scientifique", "analyse", "rapport"],
-    "étude": ["recherche", "analyse", "données", "résultat"],
-
-    "santé": ["médical", "sanitaire", "clinique", "thérapie"],
-    "maladie": ["pathologie", "syndrome", "infection"],
-
-    "politique": ["gouvernement", "législatif", "élection", "pouvoir"],
-    "loi": ["législation", "règlement", "juridique", "légal"]
-  },
-
-  "stop_words": [
-    "le", "la", "les", "un", "une", "des", "du", "de", "et", "en",
-    "pour", "dans", "avec", "sur", "par", "ce", "cette", "ces",
-    "ou", "où", "qui", "que", "quoi", "dont", "quel",
-    "informations", "disponibles", "concernant", "relatif"
-  ]
-}