Add MIT License, update README, refactor app.py, and modify requirements

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Bielikov Maksym
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -4,13 +4,13 @@ emoji: 💻
 colorFrom: blue
 colorTo: indigo
 sdk: gradio
-sdk_version: 4.26.0
+sdk_version: 6.14.0
 app_file: app.py
 fullWidth: true
-short_description: "cefrpy demo: Highlight English words according to CEFR scale"
+short_description: "Cefrpy Demo: highlight English words according to CEFR scale"
 models: ["spacy/en_core_web_sm"]
-pinned: false
+pinned: true
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at <https://huggingface.co/docs/hub/spaces-config-reference>

app.py

@@ -6,25 +6,40 @@ from cefrpy import CEFRSpaCyAnalyzer, CEFRLevel
 MODEL = "en_core_web_sm"
 
 ALL_ENTS = [
-    'CARDINAL', 'DATE', 'EVENT', 'FAC', 'GPE', 'LANGUAGE',
-    'LAW', 'LOC', 'MONEY', 'NORP', 'ORDINAL', 'ORG', 'PERCENT',
-    'PERSON', 'PRODUCT', 'QUANTITY', 'TIME', 'WORK_OF_ART'
+    "CARDINAL",
+    "DATE",
+    "EVENT",
+    "FAC",
+    "GPE",
+    "LANGUAGE",
+    "LAW",
+    "LOC",
+    "MONEY",
+    "NORP",
+    "ORDINAL",
+    "ORG",
+    "PERCENT",
+    "PERSON",
+    "PRODUCT",
+    "QUANTITY",
+    "TIME",
+    "WORK_OF_ART",
 ]
 
 DEFAULT_ENTITY_ITEMS_TO_SKIP = [
-    'QUANTITY', 'MONEY', 'LANGUAGE', 'LAW',
-    'WORK_OF_ART', 'PRODUCT', 'GPE',
-    'ORG', 'FAC', 'PERSON'
+    "QUANTITY",
+    "MONEY",
+    "LANGUAGE",
+    "LAW",
+    "WORK_OF_ART",
+    "PRODUCT",
+    "GPE",
+    "ORG",
+    "FAC",
+    "PERSON",
 ]
 
-TOKEN_ATTRIBUTES = [
-    "Token",
-    "POS",
-    "Skipped",
-    "Level",
-    "Start",
-    "End"
-]
+TOKEN_ATTRIBUTES = ["Token", "POS", "Skipped", "Level", "Start", "End"]
 
 WORDLIST_HEADER = ["Word", "Pos", "CEFR", "Level"]
 
@@ -40,6 +55,7 @@ In 2006, a Coca-Cola employee offered to sell Coca-Cola secrets to Pepsi. Pepsi
 
 Like humans, cows form strong social bonds and often have "best friends" within their herds. They display complex social behaviors, including grooming, playing, and even grieving when separated from their friends."""
 
+# Light-mode colors (used by displacy; must match the hex values in the CSS below)
 DISPLACY_RENDER_OPTIONS = {
     "colors": {
         "A1": "#b0c4de",
@@ -49,7 +65,7 @@ DISPLACY_RENDER_OPTIONS = {
         "C1": "#ffd700",
         "C2": "#ff9380",
         "SKIP": "#ffafed",
-        "UNKNOWN": "#BCAAA4"
+        "UNKNOWN": "#BCAAA4",
     }
 }
 
@@ -60,77 +76,134 @@ ABBREVIATION_MAPPING = {
     "'ve": "have",
     "'d": "had",
     "n't": "not",
-    "'ll": "will"
+    "'ll": "will",
 }
 
-LINKS_HTML = """
-<p>
-    &ensp;Github: <a href="https://github.com/Maximax67/cefrpy">link</a><br>
-    &ensp;Docs: <a href="https://maximax67.github.io/cefrpy">link</a><br>
-</p>
-"""
-
+# Minimal CSS: only the dual-theme entity colors. All other styling is unchanged.
 CSS = """
 h1 {
     padding-top: 5px;
     text-align: center;
     display:block;
 }
+
+.cefr-link-btn:hover {
+    background: #f6f8fa;
+    border-color: #999 !important;
+}
+
+.dark .cefr-link-btn:hover {
+    background: #30363d;
+    border-color: #888 !important;
+}
+
+/* Light-mode CEFR entity colors (matches DISPLACY_RENDER_OPTIONS above) */
+:root {
+    --cefr-a1:      #b0c4de;
+    --cefr-a2:      #87ceeb;
+    --cefr-b1:      #90ee90;
+    --cefr-b2:      #adff2f;
+    --cefr-c1:      #ffd700;
+    --cefr-c2:      #ff9380;
+    --cefr-skip:    #ffafed;
+    --cefr-unknown: #BCAAA4;
+}
+
+/* Dark-mode overrides — Gradio adds class="dark" to <html> */
+.dark {
+    --cefr-a1:      #1e4e8c;
+    --cefr-a2:      #0c6080;
+    --cefr-b1:      #145c2e;
+    --cefr-b2:      #4a7200;
+    --cefr-c1:      #8a6400;
+    --cefr-c2:      #952e1e;
+    --cefr-skip:    #7a2070;
+    --cefr-unknown: #4a3c38;
+}
+
+/* Override displacy's inline background colors using attribute selectors.
+   Both cases (lower and upper) are covered since different browsers/displacy
+   versions may render hex in either case. */
+mark[style*="#b0c4de"], mark[style*="#B0C4DE"] { background: var(--cefr-a1)      !important; }
+mark[style*="#87ceeb"], mark[style*="#87CEEB"] { background: var(--cefr-a2)      !important; }
+mark[style*="#90ee90"], mark[style*="#90EE90"] { background: var(--cefr-b1)      !important; }
+mark[style*="#adff2f"], mark[style*="#ADFF2F"] { background: var(--cefr-b2)      !important; }
+mark[style*="#ffd700"], mark[style*="#FFD700"] { background: var(--cefr-c1)      !important; }
+mark[style*="#ff9380"], mark[style*="#FF9380"] { background: var(--cefr-c2)      !important; }
+mark[style*="#ffafed"], mark[style*="#FFAFED"] { background: var(--cefr-skip)    !important; }
+mark[style*="#BCAAA4"], mark[style*="#bcaaa4"] { background: var(--cefr-unknown) !important; }
 """
 
 nlp = spacy.load(MODEL)
 
-def get_dict_ents(text: str, tokens: list[tuple[str, str, bool, float, int, int]]) -> dict:
+
+def get_dict_ents(
+    text: str, tokens: list[tuple[str, str, bool, float, int, int]]
+) -> dict:
     ents = []
 
     for token in tokens:
         if token[3]:
-            ents.append({
-                "start": token[4],
-                "end": token[5],
-                "label": str(CEFRLevel(round(token[3])))
-            })
+            ents.append(
+                {
+                    "start": token[4],
+                    "end": token[5],
+                    "label": str(CEFRLevel(round(token[3]))),
+                }
+            )
         elif token[0].isalpha():
-            ents.append({
-                "start": token[4],
-                "end": token[5],
-                "label": "SKIP" if token[2] else "UNKNOWN"
-            })
-
-    dict_ents = {
-        "text": text,
-        "ents": ents
-    }
+            ents.append(
+                {
+                    "start": token[4],
+                    "end": token[5],
+                    "label": "SKIP" if token[2] else "UNKNOWN",
+                }
+            )
+
+    dict_ents = {"text": text, "ents": ents}
 
     return dict_ents
 
 
-def get_cefr_tokens(text: str, ents_to_skip: list[str]) -> list[tuple[str, str, bool, float, int, int]]:
+def get_cefr_tokens(
+    text: str, ents_to_skip: list[str]
+) -> list[tuple[str, str, bool, float, int, int]]:
     doc = nlp(text)
-    text_analyzer = CEFRSpaCyAnalyzer(entity_types_to_skip=ents_to_skip, abbreviation_mapping=ABBREVIATION_MAPPING)
-    tokens = text_analyzer.analize_doc(doc)
+    text_analyzer = CEFRSpaCyAnalyzer(
+        entity_types_to_skip=ents_to_skip, abbreviation_mapping=ABBREVIATION_MAPPING
+    )
+    tokens = text_analyzer.analyze_doc(doc)
 
     return tokens
 
 
-def get_html_visualization(text: str, tokens: list[tuple[str, str, bool, float, int, int]]) -> str:
+def get_html_visualization(
+    text: str, tokens: list[tuple[str, str, bool, float, int, int]]
+) -> str:
     dict_ents = get_dict_ents(text, tokens)
-    html = displacy.render(dict_ents, manual=True, style="ent", options=DISPLACY_RENDER_OPTIONS)
+    html = displacy.render(
+        dict_ents, manual=True, style="ent", options=DISPLACY_RENDER_OPTIONS
+    )
 
     return html
 
 
-def get_wordlist_set(tokens: list[tuple[str, str, bool, float, int, int]],
-                min_level: float) -> set[tuple[str, str, bool, float, int, int]]:
+def get_wordlist_set(
+    tokens: list[tuple[str, str, bool, float, int, int]], min_level: float
+) -> set[tuple[str, str, bool, float, int, int]]:
     filtered_tokens = set()
     for word, pos, _, level, _, _ in tokens:
         if level and level >= min_level:
-            filtered_tokens.add((word.lower(), pos, str(CEFRLevel(round(level))), level))
+            filtered_tokens.add(
+                (word.lower(), pos, str(CEFRLevel(round(level))), level)
+            )
 
     return filtered_tokens
 
 
-def get_wordlist(tokens: list[tuple[str, str, bool, float, int, int]], min_level: float):
+def get_wordlist(
+    tokens: list[tuple[str, str, bool, float, int, int]], min_level: float
+):
     wordlist_set = get_wordlist_set(tokens, min_level)
     wordlist = list(wordlist_set)
     wordlist.sort()
@@ -142,7 +215,11 @@ def get_wordlist_from_dataframe(dataframe, min_level: float):
     return get_wordlist(dataframe.values, min_level)
 
 
-def process_text(text: str, ents_to_skip: list[str] | None = DEFAULT_ENTITY_ITEMS_TO_SKIP, min_level: float = DEFAULT_WORDLIST_SLIDER_LEVEL) -> tuple[list[list], str]:
+def process_text(
+    text: str,
+    ents_to_skip: list[str] = DEFAULT_ENTITY_ITEMS_TO_SKIP,
+    min_level: float = DEFAULT_WORDLIST_SLIDER_LEVEL,
+) -> tuple[list[tuple], list[tuple], str]:
     tokens = get_cefr_tokens(text, ents_to_skip)
     html = get_html_visualization(text, tokens)
     wordlist = get_wordlist(tokens, min_level)
@@ -152,15 +229,49 @@ def process_text(text: str, ents_to_skip: list[str] | None = DEFAULT_ENTITY_ITEM
 
 initial_tokens, initial_wordlist, initial_html = process_text(DEFAULT_TEXT)
 
-demo = gr.Blocks(css=CSS)
+demo = gr.Blocks()
 
 with demo:
     with gr.Row():
         with gr.Column():
             with gr.Column():
-                with gr.Row():
-                    gr.Markdown("# Gradio Demo: cefrpy")
-                    gr.HTML(LINKS_HTML)
+                gr.HTML("""
+                    <div style="display:flex; align-items:center; justify-content:space-between; flex-wrap:wrap; gap:8px;">
+                        <h1 style="margin:0; font-size:1.6rem; font-weight:700;">Gradio Demo: cefrpy</h1>
+                        <div style="display:flex; gap:10px; align-items:center; flex-wrap:wrap;">
+                            <a class="cefr-link-btn" href="https://github.com/Maximax67/cefrpy" target="_blank"
+                            style="display:inline-flex; align-items:center; gap:6px; padding:5px 12px;
+                                border-radius:6px; border:1px solid #d0d7de; text-decoration:none;
+                                color:inherit; font-size:0.9rem; font-weight:500; transition:background 0.15s, border-color 0.15s;">
+                                <svg width="18" height="18" viewBox="0 0 16 16" fill="currentColor">
+                                    <path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38
+                                    0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13
+                                    -.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66
+                                    .07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15
+                                    -.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0
+                                    1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82
+                                    1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01
+                                    1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z"/>
+                                </svg>
+                                GitHub
+                            </a>
+                            <a class="cefr-link-btn" href="https://maximax67.github.io/cefrpy" target="_blank"
+                            style="display:inline-flex; align-items:center; gap:6px; padding:5px 12px;
+                                    border-radius:6px; border:1px solid #d0d7de; text-decoration:none;
+                                    color:inherit; font-size:0.9rem; font-weight:500; transition:background 0.15s, border-color 0.15s;">
+                                <svg width="18" height="18" viewBox="0 0 24 24" fill="none"
+                                    stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+                                    <path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"/>
+                                    <polyline points="14 2 14 8 20 8"/>
+                                    <line x1="16" y1="13" x2="8" y2="13"/>
+                                    <line x1="16" y1="17" x2="8" y2="17"/>
+                                    <polyline points="10 9 9 9 8 9"/>
+                                </svg>
+                                Docs
+                            </a>
+                        </div>
+                    </div>
+                """)
 
                 with gr.Row():
                     text_input = gr.TextArea(
@@ -168,27 +279,23 @@ with demo:
                         interactive=True,
                         max_lines=500,
                         label="Input Text",
-                        show_copy_button=True
+                        buttons=["copy"],
                     )
 
                 with gr.Row():
                     ent_input = gr.CheckboxGroup(
                         ALL_ENTS,
                         value=DEFAULT_ENTITY_ITEMS_TO_SKIP,
-                        label="Entity types to skip CEFR"
+                        label="Entity types to skip CEFR",
                     )
 
                 with gr.Row():
                     clear_button = gr.ClearButton(text_input)
-
-                    render_button = gr.Button(
-                        "Render",
-                        variant="primary"
-                    )
+                    render_button = gr.Button("Render", variant="primary")
 
         with gr.Column():
             with gr.Row():
-                gr.Markdown("# Words CEFR level visualization")
+                gr.Markdown("# Words CEFR level visualization", padding=True)
 
             with gr.Row():
                 rendered_html = gr.HTML(initial_html)
@@ -196,34 +303,37 @@ with demo:
     with gr.Row():
         with gr.Column():
             with gr.Row():
-                tokens_output = gr.Dataframe(headers=TOKEN_ATTRIBUTES, value=initial_tokens, interactive=False)
+                tokens_output = gr.Dataframe(
+                    headers=TOKEN_ATTRIBUTES, value=initial_tokens, interactive=False
+                )
 
         with gr.Column():
             with gr.Row():
                 min_level_slider = gr.Slider(
                     minimum=1.0,
-                    maximum=6.0, 
+                    maximum=6.0,
                     value=DEFAULT_WORDLIST_SLIDER_LEVEL,
                     step=0.02,
                     interactive=True,
-                    label="Min level to generate word list"
+                    label="Min level to generate word list",
                 )
 
             with gr.Row():
-                wordlist = gr.Dataframe(headers=WORDLIST_HEADER, value=initial_wordlist, interactive=False)
+                wordlist = gr.Dataframe(
+                    headers=WORDLIST_HEADER, value=initial_wordlist, interactive=False
+                )
 
     render_button.click(
         process_text,
         inputs=[text_input, ent_input],
         outputs=[tokens_output, wordlist, rendered_html],
-        api_name="process_text"
+        api_name="process_text",
     )
 
     min_level_slider.release(
         get_wordlist_from_dataframe,
         inputs=[tokens_output, min_level_slider],
         outputs=[wordlist],
-        api_name=False
     )
 
-demo.launch(show_api=True)
+demo.launch(css=CSS)

requirements.txt

@@ -1,4 +1,4 @@
-cefrpy
-spacy~=3.7.4
+cefrpy>=1.0.2
+spacy>=3.7,<4.0
 
 https://huggingface.co/spacy/en_core_web_sm/resolve/main/en_core_web_sm-any-py3-none-any.whl