Update skeleton ready with ezbee dzbee

app.py

@@ -1,34 +1,106 @@
-"""Prep __main__.py."""
+"""Prep __main__.py.
+
+https://share.streamlit.io/deploy
+    Advanced settings...
+        Python version
+            3.7
+            3.8
+            3.9*
+            3.10
+
+https://docs.streamlit.io/knowledge-base/using-streamlit/hide-row-indices-displaying-dataframe
+    Hide row indices when displaying a dataframe
+# CSS to inject contained in a string
+hide_table_row_index = '''
+            <style>
+            tbody th {display:none}
+            .blank {display:none}
+            </style>
+            '''
+# Inject CSS with Markdown
+st.markdown(hide_table_row_index, unsafe_allow_html=True)
+
+# Display a static table
+st.table(df)
+
+# Hide row indices with st.dataframe
+# CSS to inject contained in a string
+hide_dataframe_row_index = '''
+            <style>
+            .row_heading.level0 {display:none}
+            .blank {display:none}
+            </style>
+           '''
+# Inject CSS with Markdown
+st.markdown(hide_dataframe_row_index, unsafe_allow_html=True)
+
+# Display an interactive table
+st.dataframe(df)
+
+https://medium.com/@avra42/streamlit-python-cool-tricks-to-make-your-web-application-look-better-8abfc3763a5b
+hide_menu_style = '''
+        <style>
+        #MainMenu {visibility: hidden; }
+        footer {visibility: hidden;}
+        </style>
+        '''
+st.markdown(hide_menu_style, unsafe_allow_html=True)
+
+"""
 # pylint: disable=invalid-name
 import os
+import sys
+import time
 from pathlib import Path
+from types import SimpleNamespace
 from typing import Optional
 
+import loguru
+import logzero
 import pandas as pd
-
 import streamlit as st
-from streamlit import session_state as state
-from types import SimpleNamespace
-
-import logzero
+from loguru import logger as loggu
 from logzero import logger
 from set_loglevel import set_loglevel
+from streamlit import session_state as state
 
 from litbee import __version__, litbee
-from litbee.files2df import files2df
-from litbee.utils import sb_front_cover, instructions, menu_items
-from litbee.ezbee_page import ezbee_page
-from litbee.dzbee_page import dzbee_page
-from litbee.xbee_page import xbee_page
+from litbee.options import options
+
+# from litbee.files2df import files2df
+# from litbee.utils import sb_front_cover, instructions, menu_items
+# from litbee.ezbee_page import ezbee_page
+# from litbee.dzbee_page import dzbee_page
+# from litbee.xbee_page import xbee_page
+from litbee.utils import menu_items
+
+# from ezbee import ezbee
 
 os.environ["TZ"] = "Asia/Shanghai"
-os.environ["LOGLEVEL"] = "10"
+time.tzset()
+os.environ["LOGLEVEL"] = "10"  # uncomment this in dev
 logzero.loglevel(set_loglevel())
 
+loggu.remove()
+_ = (
+    "<green>{time:YY-MM-DD HH:mm:ss}</green> | "
+    "<level>{level: <5}</level> | <level>{message}</level> "
+    "<cyan>{name}</cyan>:<cyan>{line}</cyan>"
+)
+loggu.add(
+    sys.stderr,
+    format=_,
+    level=set_loglevel(),
+    colorize=True,
+)
+
+# from PIL import Image
+# page_icon=Image.open("icon.ico"),
 st.set_page_config(
     page_title=f"litbee v{__version__}",
-    page_icon="🧊",
-    layout="wide",
+    # page_icon="🧊",
+    page_icon="🐝",
+    # layout="wide",
     initial_sidebar_state="auto",  # "auto" or "expanded" or "collapsed",
     menu_items=menu_items,
 )
@@ -37,47 +109,28 @@ st.set_page_config(
 pd.set_option("display.precision", 2)
 pd.options.display.float_format = "{:,.2f}".format
 
-
+_ = dict(
+    beetype="ezbee",
+    src_filename="",
+    tgt_filename="",
+    src_fileio=b"",
+    tgt_fileio=b"",
+    src_file="",
+    tgt_file="",
+    list1=[""],
+    list2=[""],
+    df=None,
+    df_a=None,
+    df_s_a=None,
+)
 if "ns" not in state:
-    state.ns = SimpleNamespace()
+    state.ns = SimpleNamespace(**_)
+state.ns.list = [*_]
 
 
 def main():
-    # instructions()
-
-    sb_front_cover()
-
-    try:
-        _ = state.ns.df
-        state.ns.count += 1
-        logger.debug(" run: %s", state.ns.count)
-    except AttributeError:
-        logger.debug("first run")
-        # df = files2df("data/en.txt", "data/zh.txt")
-        df = files2df("data/test_en.txt", "data/test_zh.txt")
-        state.ns.count = 1
-        state.ns.df = df
-
-    # multi-page setup
-    menu = {
-        "ezbee": ezbee_page,
-        "dzbee": dzbee_page,
-        "xbee": xbee_page,
-    }
-    selection = st.sidebar.radio("", menu)
-    page = menu[selection]
-
-    # page.app()
-    page()
-
-    # 'items', 'keys', values, 'to_dict', 'update', 'values'
-    # logger.debug("state.ns: %s", state.ns)
-
-    st.write(f"run: {state.ns.count}")
-    # st.dataframe(state.ns.df)
-
-    # st.markdown(html_string, unsafe_allow_html=True)
-    # st.markdown(state.ns.df.to_html(), unsafe_allow_html=True)
+    """Bootstrap."""
+    options()
 
 
 main()

config.toml

@@ -0,0 +1,6 @@
+[theme]
+primaryColor="#2214c7"
+backgroundColor="#ffffff"
+secondaryBackgroundColor="#e8eef9"
+textColor="#000000"
+font="sans serif"

data/en - Copy.txt

@@ -0,0 +1,8 @@
+[Young Warrior] Kingold(...) 2021-12-30 22:27:37
+It seems that the standalone version can
+omit the GUI and specify the two files to be aligned directly on the command line.
+
+
+But if it's not the GUI module that's taking up space, then
+ removing it won't help compress the size of the whole package.
+

data/zh - Copy.txt

@@ -0,0 +1,7 @@
+【少侠】Kingold(...) 2021-12-30 22:27:37
+单机版貌似可以省略掉图形界面，直接
+命令行指定两个待对齐文件。
+
+不过如果占地方的
+
+不是图形界面的模块，那去掉了也对压缩整个包的大小没帮助。

litbee/__main__.py

@@ -2,15 +2,14 @@
 # pylint: disable=invalid-name
 import os
 from pathlib import Path
-from typing import Optional
-
-import streamlit as st
-from streamlit import session_state as state
 from types import SimpleNamespace
+from typing import Optional
 
 import logzero
+import streamlit as st
 from logzero import logger
 from set_loglevel import set_loglevel
+from streamlit import session_state as state
 
 from litbee import __version__, litbee
 from litbee.files2df import files2df
@@ -22,6 +21,7 @@ logzero.loglevel(set_loglevel())
 if "ns" not in state:
     state.ns = SimpleNamespace()
 
+
 def main():
     logger.debug("state: %s", state)
 
@@ -29,4 +29,5 @@ def main():
     state.ns.df = df
     logger.debug("state: %s", state)
 
+
 main()

litbee/dzbee_page.py

@@ -1,6 +1,8 @@
 """Display dzbee page."""
-import streamlit as st
 import pandas as pd
+import streamlit as st
+from loguru import logger as loggu
+from logzero import logger
 
 
 def dzbee_page():
@@ -14,4 +16,5 @@ def dzbee_page():
         logger.error(exc)
         df = pd.DataFrame([[""]])
 
+    loggu.debug(" df ")
     st.table(df)

litbee/ezbee_page.py

@@ -1,9 +1,32 @@
 """Display ezbee page."""
-import streamlit as st
-import pandas as pd
+from functools import partial
 
+import logzero
+import pandas as pd
+import streamlit as st
+from ezbee import ezbee
+from ezbee.gen_pairs import gen_pairs
+from loguru import logger as loggu
+from logzero import logger
+from set_loglevel import set_loglevel
 from st_aggrid import AgGrid
 from st_aggrid.grid_options_builder import GridOptionsBuilder
+from streamlit import session_state as state
+
+logzero.loglevel(set_loglevel())
+
+
+def st_radio_horizontal(*args, **kwargs):
+    """Trick to have horizontal st radio to simulate tabs."""
+    col, _ = st.columns(2)
+    with col:
+        # st.write('<style> div[data-testid=column] > div > div > div > div.stRadio > div{flex-direction: row;}</style>', unsafe_allow_html=True)
+        # return st.radio(*args, **kwargs)
+        st.write(
+            "<style> div[data-testid=stSidebar] > div > div > div > div > div > div > div.stRadio > div{flex-direction: row;}</style>",
+            unsafe_allow_html=True,
+        )
+        return st.sidebar.radio(*args, **kwargs)
 
 
 def ezbee_page():
@@ -12,11 +35,13 @@ def ezbee_page():
     # st.write('### ezbee')
     # st.write('Welcome to app1')
 
+    _ = """
     try:
         df = st.session_state.ns.df
     except Exception as exc:
         logger.error(exc)
         df = pd.DataFrame([[""]])
+    # """
 
     # st.table(df)  # looks alright
 
@@ -24,19 +49,14 @@ def ezbee_page():
     # bigger, no pagination
     # st.markdown(df.to_html(), unsafe_allow_html=True)
 
-    gb = GridOptionsBuilder.from_dataframe(df)
-    gb.configure_pagination()
-    options = {
-        "resizable": True,
-        "autoHeight": True,
-        "wrapText": True,
-        "editable": True,
-    }
-    gb.configure_default_column(**options)
-    gridOptions = gb.build()
-
     # ag_grid smallish, editable, probably slower
 
+    if "df" not in globals():
+        logger.debug(" df not defined, return")
+        return None
+
+    df = pd.DataFrame([["", "", ""]], columns=["text1", "text2", "llh"])
+
     df_exp = st.expander("to be aligned", expanded=False)
     with df_exp:
         st.write(df)  # too small
@@ -53,11 +73,57 @@ def ezbee_page():
         )
     # """
 
-    st.write("double-click a cell to edit")
+    list1 = [elm.strip() for elm in df.text1 if elm.strip()]
+    list2 = [elm.strip() for elm in df.text2 if elm.strip()]
+    logger.info("Processing data...")
+    try:
+        aset = ezbee(
+            list1,
+            list2,
+            # eps=eps,
+            # min_samples=min_samples,
+        )
+    except Exception as e:
+        logger.error("aset = ezbee(...) exc: %s", e)
+        aset = ""
+        return None
+
+    # fastlid changed logger.level is changed to 20
+    # turn back to loglevel
+    logzero.loglevel(set_loglevel())
+    if aset:
+        logger.debug("aset: %s...%s", aset[:3], aset[-3:])
+
+    # st.write(aset)
+
+    aligned_pairs = gen_pairs(list1, list2, aset)
+    if aligned_pairs:
+        logger.debug("%s...%s", aligned_pairs[:3], aligned_pairs[-3:])
+
+    df_a = pd.DataFrame(aligned_pairs, columns=["text1", "text2", "llh"])
+
+    # insert seq no
+    df_a.insert(0, "sn", range(len(df_a)))
+
+    gb = GridOptionsBuilder.from_dataframe(df_a)
+    gb.configure_pagination(paginationAutoPageSize=True)
+    options = {
+        "resizable": True,
+        "autoHeight": True,
+        "wrapText": True,
+        "editable": True,
+    }
+    gb.configure_default_column(**options)
+    gridOptions = gb.build()
+
+    st.write("aligned (double-click a cell to edit)")
     agdf = AgGrid(
-        df,
-        # fit_columns_on_grid_load=True,
-        editable=True,
+        # df,
+        df_a,
         gridOptions=gridOptions,
-        key="outside"
-    )
+        key="outside",
+        editable=True,
+        width="100%",
+        height=500,
+        # fit_columns_on_grid_load=True,
+    )

litbee/fetch_paste.py

@@ -0,0 +1,9 @@
+"""Display from paste."""
+import pandas as pd
+import streamlit as st
+from logzero import logger
+
+
+def fetch_paste():
+    """Display from paste."""
+    st.write("Coming soon")

litbee/fetch_upload.py

@@ -0,0 +1,198 @@
+"""Fetch content from upload.
+
+org ezbee_page.py.
+"""
+from functools import partial
+from itertools import zip_longest
+
+import logzero
+import pandas as pd
+import streamlit as st
+from ezbee import ezbee
+from dzbee import dzbee
+from ezbee.gen_pairs import gen_pairs  # aset2pairs?
+from loguru import logger as loggu
+from logzero import logger
+from set_loglevel import set_loglevel
+from st_aggrid import AgGrid
+from st_aggrid.grid_options_builder import GridOptionsBuilder
+from streamlit import session_state as state
+
+logzero.loglevel(set_loglevel())
+
+
+def fetch_upload():
+    """Fetch content from upload."""
+
+    # src_fileio tgt_fileio
+    sb_pick_files = st.sidebar.expander("Pick two files", expanded=True)
+    with sb_pick_files:
+        src_fileio = st.file_uploader(
+            "Choose source file (utf8 txt)",
+            type=[
+                "txt",
+            ],
+            key="src_text",
+            # accept_multiple_files=True,
+            # accept_multiple_files=False,
+        )
+
+        tgt_fileio = st.file_uploader(
+            "Choose target file (utf8 txt)",
+            type=[
+                "txt",
+            ],
+            key="tgt_text",
+            # accept_multiple_files=True,
+        )
+
+    # logger.debug(" len(src_fileio): %s", len(src_fileio))
+    # logger.debug(" len(tgt_fileio): %s", len(tgt_fileio))
+
+    if src_fileio:
+        logger.debug(" type(src_fileio): %s", type(src_fileio))
+        if isinstance(src_fileio, list):
+            logger.debug(" len(src_fileio): %s", len(src_fileio))
+            logger.debug("src_fileio[-1].name: [%s]", src_fileio[-1].name)
+            filenames = [elm.name for elm in src_fileio]
+            logger.debug("src_fileio  names: %s", filenames)
+
+            # state.ns.src_fileio = src_fileio
+            state.ns.src_file = src_fileio[-1].getvalue().decode()
+            state.ns.src_filename = src_fileio[-1].name
+        else:
+            logger.debug("src_fileio.name: [%s]", src_fileio.name)
+            filenames = [src_fileio.name]
+            logger.debug("src_fileio  names: %s", filenames)
+
+            # state.ns.src_fileio = src_fileio
+            state.ns.src_file = src_fileio.getvalue().decode()
+            state.ns.src_filename = src_fileio.name
+
+    if tgt_fileio:
+        if isinstance(tgt_fileio, list):
+            logger.warning("not set to handle multiple files")
+            logger.warning("set accept_multiple_files=False in the meantime")
+        else:
+            state.ns.tgt_file = tgt_fileio.getvalue().decode()
+            state.ns.tgt_filename = tgt_fileio.name
+
+    try:
+        _ = state.ns.src_file.splitlines()
+        list1 = [elm.strip() for elm in _ if elm.strip()]
+        _ = state.ns.tgt_file.splitlines()
+        list2 = [elm.strip() for elm in _ if elm.strip()]
+    except Exception as exc:
+        logger.error(exc)
+        list1 = [""]
+        list2 = [""]
+    state.ns.list1 = list1[:]
+    state.ns.list2 = list2[:]
+
+    df = pd.DataFrame(zip_longest(list1, list2, fillvalue=""))
+    try:
+        df.columns = ["text1", "text2"]
+    except Exception as exc:
+        logger.debug("df: \n%s", df)
+        logger.error("%s", exc)
+
+    state.ns.df = df
+    logger.debug("df: %s", df)
+
+    # st.table(df)  # looks alright
+
+    # stlyed pd dataframe?
+    # bigger, no pagination
+    # st.markdown(df.to_html(), unsafe_allow_html=True)
+
+    # ag_grid smallish, editable, probably slower
+
+    # if "df" not in globals() or "df" not in locals():
+    if "df" not in locals():
+        logger.debug(" df not defined, return")
+
+    if df.empty:
+        logger.debug(" df.empty, return")
+        return None
+
+    # df = pd.DataFrame([["", "", ""]], columns=["text1", "text2", "llh"])
+
+    df_exp = st.expander("to be aligned", expanded=False)
+    with df_exp:
+        st.write(df)  # too small
+
+    _ = """
+    ag_exp = st.expander("done aligned")  # , expanded=False
+    with ag_exp:
+        agdf = AgGrid(
+            df,
+            # fit_columns_on_grid_load=True,
+            editable=True,
+            gridOptions=gridOptions,
+            key="ag_exp",
+        )
+    # """
+
+    list1 = [elm.strip() for elm in df.text1 if elm.strip()]
+    list2 = [elm.strip() for elm in df.text2 if elm.strip()]
+    logger.info("Processing data...")
+    if state.ns.beetype in ["ezbee", "dzbee"]:
+        try:
+            # aset = ezbee(
+            aset = globals()[state.ns.beetype](
+                list1,
+                list2,
+                # eps=eps,
+                # min_samples=min_samples,
+            )
+        except Exception as e:
+            logger.error("aset = ezbee(...) exc: %s", e)
+            aset = ""
+            # st.write(e)
+            st.write("Collecting inputs...")
+            return None
+    else:
+        st.write(f"{state.ns.beetype} coming soon...")
+        return None
+
+    # fastlid changed logger.level is changed to 20
+    # turn back to loglevel
+    logzero.loglevel(set_loglevel())
+    if aset:
+        logger.debug("aset: %s...%s", aset[:3], aset[-3:])
+        # logger.debug("aset[:10]: %s", aset[:10])
+
+    # st.write(aset)
+
+    aligned_pairs = gen_pairs(list1, list2, aset)
+    if aligned_pairs:
+        logger.debug("%s...%s", aligned_pairs[:3], aligned_pairs[-3:])
+        # logger.debug("aligned_pairs[:20]: \n%s", aligned_pairs[:20])
+
+    df_a = pd.DataFrame(aligned_pairs, columns=["text1", "text2", "llh"])
+
+    # insert seq no
+    df_a.insert(0, "sn", range(len(df_a)))
+
+    gb = GridOptionsBuilder.from_dataframe(df_a)
+    gb.configure_pagination(paginationAutoPageSize=True)
+    options = {
+        "resizable": True,
+        "autoHeight": True,
+        "wrapText": True,
+        "editable": True,
+    }
+    gb.configure_default_column(**options)
+    gridOptions = gb.build()
+
+    st.write("aligned (double-click a cell to edit, drag column header to adjust widths)")
+    agdf = AgGrid(
+        # df,
+        df_a,
+        gridOptions=gridOptions,
+        key="outside",
+        editable=True,
+        # width="100%",  # width parameter is deprecated
+        height=500,
+        # fit_columns_on_grid_load=True,
+    )

litbee/fetch_urls.py

@@ -0,0 +1,9 @@
+"""Fetch from urls."""
+import pandas as pd
+import streamlit as st
+from logzero import logger
+
+
+def fetch_urls():
+    """Display from urls."""
+    st.write("Coming soon")

litbee/files2df.py

@@ -1,9 +1,11 @@
 """Convert two iesl to pandas.DataFrame."""
 # pylint: disable=invalid-name
 
-from itertools import zip_longest
 import tempfile
+from itertools import zip_longest
+
 import pandas as pd
+
 from litbee.process_upload import process_upload
 
 

litbee/options.py

@@ -0,0 +1,82 @@
+"""Load content."""
+# pylint: disable=invalid-name
+from functools import partial
+
+import streamlit as st
+from loguru import logger as loggu
+from logzero import logger
+from streamlit import session_state as state
+
+from litbee.fetch_paste import fetch_paste
+
+# from litbee.ezbee_page import ezbee_page
+# from litbee.dzbee_page import dzbee_page
+# from litbee.xbee_page import xbee_page
+from litbee.fetch_upload import fetch_upload
+from litbee.fetch_urls import fetch_urls
+from litbee.files2df import files2df
+from litbee.utils import instructions, sb_front_cover
+
+
+def options():
+    """Load content."""
+    sb_front_cover()
+
+    try:
+        _ = state.ns.df
+        state.ns.count += 1
+        logger.debug(" run: %s", state.ns.count)
+    except AttributeError:
+        logger.debug("first run")
+        # df = files2df("data/en.txt", "data/zh.txt")
+        df = files2df("data/test_en.txt", "data/test_zh.txt")
+        state.ns.count = 1
+        state.ns.df = df
+
+    # horizonral radio
+    st.sidebar.write(
+        "<style>div.row-widget.stRadio > div{flex-direction:row;}</style>",
+        unsafe_allow_html=True,
+    )
+
+    beetype_list = ["ezbee", "dzbee", "xbee"]
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        beetype = st.sidebar.radio("Pick a bee", beetype_list)
+        state.ns.beetype = beetype
+
+    if beetype not in ["ezbee", "dzbee"]:
+        st.write("Coming soon")
+        return None
+
+    # multi-page setup
+    menu = {
+        "upload": fetch_upload,
+        "paste": fetch_paste,
+        "urls": fetch_urls,
+    }
+
+    with col2:
+        source = st.sidebar.radio("Source", [*menu])
+
+    # item = menu[source]
+    # item()
+
+    menu[source]()
+
+    # if hasattr(state.ns, "df"): delattr(state.ns, "df")
+
+    # logger.debug(" state.ns: %s", state.ns)
+
+    # show state.ns[:6]
+    loggu.debug(f" state.ns.list: {state.ns.list}")
+
+    _ = map(partial(getattr, state.ns), state.ns.list[:3])
+    logger.debug(" state.ns.list[:3]: %s", str([*_]))
+
+    st.write(f"run: {state.ns.count}")
+    loggu.debug(f"run: {state.ns.count}")
+
+    fileio_slot = st.empty()

litbee/process_upload.py

@@ -1,9 +1,9 @@
 """Process uploads."""
 # pylint: disable=invalid-name, unused-import
+import tempfile
+from pathlib import Path
 from typing import Union
 
-from pathlib import Path
-import tempfile
 import cchardet
 from logzero import logger
 
@@ -37,7 +37,7 @@ def process_upload(upload: Union[str, tempfile._TemporaryFileWrapper, bytes]) ->
     ]
     # check .txt .md ''(no suffix)
     if fpath.suffix.lower() not in suffixes:
-        logger.warning('suffix: [%s] not in %s', fpath.suffix, suffixes)
+        logger.warning("suffix: [%s] not in %s", fpath.suffix, suffixes)
         # return "File type not supported, yet."
 
     try:
@@ -76,29 +76,3 @@ def process_upload(upload: Union[str, tempfile._TemporaryFileWrapper, bytes]) ->
     logger.warning("%s", msg)
 
     return msg
-
-
-_ = '''  # colab gradio-file-inputs-upload.ipynb
-# file_to_text/process_file
-def zip_to_text(file_obj):
-  """
-  # zf = zipfile.ZipFile('german-recipes-dataset.zip')
-  zf = file_obj
-  namelist = zipfile.ZipFile.namelist(zf);
-  # filename = zf.open(namelist[0]);
-  file_contents = []
-  for filename in namelist:
-    with zf.open(filename) as fhandle:
-      file_contents.append(fhandle.read().decode())
-  """
-  # fileobj is <class 'tempfile._TemporaryFileWrapper'>
-
-  # gr.inputs.File("bytes")
-  if isinstance(file_obj, bytes):
-    data = file_obj.decode()
-    return f"{type(file_obj)}\n{dir(file_obj)}\n{data}"
-
-  # "file"/gr.inputs.File("file")  file_obj.name: /tmp/READMEzm8hc5ze.md
-  data = Path(file_obj.name).read_bytes()
-  return f"{file_obj.name} {type(file_obj)}\n{dir(file_obj)} \n{data}"
-# '''

litbee/utils.py

@@ -1,7 +1,8 @@
 """Prep front cover for sidebar (based on st-bumblebee-st_app.py)."""
-import streamlit as st
 from textwrap import dedent
+
 import logzero
+import streamlit as st
 from logzero import logger
 from set_loglevel import set_loglevel
 
@@ -9,7 +10,8 @@ from litbee import __version__
 
 logzero.loglevel(set_loglevel())
 
-msg = dedent("""
+msg = dedent(
+    """
     What would you like to do?
     The following alignment engines are available.
 
@@ -22,7 +24,8 @@ msg = dedent("""
     **DL-Engin**: based on machine learning, multilingual, one para/sent takes about 1s.
     """
 ).strip()
-msg = dedent("""
+msg = dedent(
+    """
     * ezbee: english-chinese, fast para-align
 
     * dzbee: german-chinese, fast para-align
@@ -46,7 +49,8 @@ def sb_front_cover():
         st.markdown(msg)
 
 
-intructins = dedent(f"""
+intructins = dedent(
+    f"""
     *   Set up options in the left sidebar
 
     *   Click expanders / +: to reveal more details; -: to hide them
@@ -67,7 +71,8 @@ def instructions():
     logger.debug("instructions exit")
 
 
-about = dedent(f"""
+about = dedent(
+    f"""
     # litbee {__version__}
 
     https://bumblebee.freeforums.net/thread/5/litbee or head to 桃花元 （qq group 316287378）
@@ -75,7 +80,7 @@ about = dedent(f"""
 ).strip()
 
 menu_items = {
-    'Get Help': 'https://bumblebee.freeforums.net/thread/5/litbee',
-    'Report a bug': "https://github.com/ffreemt/litbee/issues",
-    'About': about,
-}
+    "Get Help": "https://bumblebee.freeforums.net/thread/5/litbee",
+    "Report a bug": "https://github.com/ffreemt/litbee/issues",
+    "About": about,
+}

litbee/xbee_page.py

@@ -1,12 +1,13 @@
 """Display xbee page."""
-import streamlit as st
 import pandas as pd
+import streamlit as st
+from logzero import logger
 
 
 def xbee_page():
     """Display xbee page."""
     # st.title('dzbee')
-    st.write('Coming soon')
+    st.write("Coming soon")
 
     try:
         df = st.session_state.ns.df

main_example.py

@@ -0,0 +1,124 @@
+"""Prep __main__.py.
+
+https://share.streamlit.io/deploy
+    Advanced settings...
+        Python version
+            3.7
+            3.8
+            3.9*
+            3.10
+
+https://docs.streamlit.io/knowledge-base/using-streamlit/hide-row-indices-displaying-dataframe
+    Hide row indices when displaying a dataframe
+# CSS to inject contained in a string
+hide_table_row_index = '''
+            <style>
+            tbody th {display:none}
+            .blank {display:none}
+            </style>
+            '''
+# Inject CSS with Markdown
+st.markdown(hide_table_row_index, unsafe_allow_html=True)
+
+# Display a static table
+st.table(df)
+
+# Hide row indices with st.dataframe
+# CSS to inject contained in a string
+hide_dataframe_row_index = '''
+            <style>
+            .row_heading.level0 {display:none}
+            .blank {display:none}
+            </style>
+           '''
+# Inject CSS with Markdown
+st.markdown(hide_dataframe_row_index, unsafe_allow_html=True)
+
+# Display an interactive table
+st.dataframe(df)
+
+https://medium.com/@avra42/streamlit-python-cool-tricks-to-make-your-web-application-look-better-8abfc3763a5b
+hide_menu_style = '''
+        <style>
+        #MainMenu {visibility: hidden; }
+        footer {visibility: hidden;}
+        </style>
+        '''
+st.markdown(hide_menu_style, unsafe_allow_html=True)
+
+"""
+# pylint: disable=invalid-name
+import os
+import sys
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Optional
+
+import loguru
+import logzero
+import pandas as pd
+import streamlit as st
+from loguru import logger as loggu
+from logzero import logger
+from set_loglevel import set_loglevel
+from streamlit import session_state as state
+
+from litbee import __version__, litbee
+from litbee.options import options
+
+# from litbee.files2df import files2df
+# from litbee.utils import sb_front_cover, instructions, menu_items
+# from litbee.ezbee_page import ezbee_page
+# from litbee.dzbee_page import dzbee_page
+# from litbee.xbee_page import xbee_page
+from litbee.utils import menu_items
+
+# from ezbee import ezbee
+
+
+
+os.environ["TZ"] = "Asia/Shanghai"
+os.environ["LOGLEVEL"] = "10"  # uncomment this in dev
+logzero.loglevel(set_loglevel())
+
+loggu.remove()
+_ = (
+    "<green>{time:YY-MM-DD HH:mm:ss}</green> | "
+    "<level>{level: <5}</level> | <level>{message}</level> "
+    "<cyan>{name}</cyan>:<cyan>{line}</cyan>"
+)
+loggu.add(
+    sys.stderr,
+    format=_,
+    level=set_loglevel(),
+    colorize=True,
+)
+
+# from PIL import Image
+# page_icon=Image.open("icon.ico"),
+st.set_page_config(
+    page_title=f"litbee v{__version__}",
+    # page_icon="🧊",
+    page_icon="🐝",
+    # layout="wide",
+    initial_sidebar_state="auto",  # "auto" or "expanded" or "collapsed",
+    menu_items=menu_items,
+)
+
+# pd.set_option("precision", 2)
+pd.set_option("display.precision", 2)
+pd.options.display.float_format = "{:,.2f}".format
+
+
+_ = dict(beetype="ezbee", src_filename="", tgt_filename="", src_fileio=b"", tgt_fileio=b"", src_file="", tgt_file="", list1=[], list2=[], df=None, df_a=None, df_s_a=None,)
+if "ns" not in state:
+    state.ns = SimpleNamespace(**_)
+state.ns.list = [*_]
+
+
+def main():
+    """Bootstrap."""
+    options()
+
+
+main()

poetry.lock

@@ -1,3 +1,23 @@
+[[package]]
+name = "about-time"
+version = "3.1.1"
+description = "Easily measure timing and throughput of code blocks, with beautiful human friendly representations."
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "alive-progress"
+version = "2.4.1"
+description = "A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!"
+category = "main"
+optional = false
+python-versions = ">=3.7, <4"
+
+[package.dependencies]
+about-time = "3.1.1"
+grapheme = "0.6.0"
+
 [[package]]
 name = "altair"
 version = "4.2.0"
@@ -56,6 +76,17 @@ cffi = ">=1.0.1"
 dev = ["pytest", "cogapp", "pre-commit", "wheel"]
 tests = ["pytest"]
 
+[[package]]
+name = "aset2pairs"
+version = "0.1.0"
+description = "Convert aset to block pairs"
+category = "main"
+optional = false
+python-versions = ">=3.8.3,<4.0.0"
+
+[package.dependencies]
+logzero = ">=1.7.0,<2.0.0"
+
 [[package]]
 name = "asttokens"
 version = "2.0.5"
@@ -231,6 +262,17 @@ category = "main"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
+[[package]]
+name = "commonmark"
+version = "0.9.1"
+description = "Python parser for the CommonMark Markdown spec"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.extras]
+test = ["flake8 (==3.7.8)", "hypothesis (==3.55.3)"]
+
 [[package]]
 name = "debugpy"
 version = "1.6.0"
@@ -255,6 +297,27 @@ category = "main"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
+[[package]]
+name = "dzbee"
+version = "0.1.1a2"
+description = "pack_name descr"
+category = "main"
+optional = false
+python-versions = ">=3.8.3,<4.0.0"
+
+[package.dependencies]
+aset2pairs = ">=0.1.0,<0.2.0"
+cchardet = ">=2.1.7,<3.0.0"
+icecream = ">=2.1.1,<3.0.0"
+install = ">=1.3.5,<2.0.0"
+Jinja2 = ">=3.1.2,<4.0.0"
+json-de2zh = "0.1.1-alpha.0"
+logzero = ">=1.7.0,<2.0.0"
+Morfessor = ">=2.0.6,<3.0.0"
+polyglot = ">=16.7.4,<17.0.0"
+typer = ">=0.4.1,<0.5.0"
+XlsxWriter = ">=3.0.3,<4.0.0"
+
 [[package]]
 name = "entrypoints"
 version = "0.4"
@@ -404,6 +467,17 @@ python-versions = ">=3.7"
 [package.dependencies]
 gitdb = ">=4.0.1,<5"
 
+[[package]]
+name = "grapheme"
+version = "0.6.0"
+description = "Unicode grapheme helpers"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.extras]
+test = ["pytest", "sphinx", "sphinx-autobuild", "wheel", "twine"]
+
 [[package]]
 name = "icecream"
 version = "2.1.2"
@@ -596,6 +670,31 @@ category = "main"
 optional = false
 python-versions = ">=3.6"
 
+[[package]]
+name = "json-de2zh"
+version = "0.1.1a0"
+description = "pack_name descr"
+category = "main"
+optional = false
+python-versions = ">=3.8.3,<4.0.0"
+
+[package.dependencies]
+alive-progress = ">=2.4.1,<3.0.0"
+cmat2aset = ">=0.1.0-alpha.7,<0.2.0"
+fast-scores = ">=0.1.2,<0.2.0"
+fastlid = ">=0.1.7,<0.2.0"
+icecream = ">=2.1.1,<3.0.0"
+install = ">=1.3.5,<2.0.0"
+joblib = ">=1.1.0,<2.0.0"
+nltk = ">=3.7,<4.0"
+numpy = ">=1.22.3,<2.0.0"
+rich = ">=12.4.1,<13.0.0"
+set-loglevel = ">=0.1.2,<0.2.0"
+simplemma = "0.3.0"
+sklearn = ">=0.0,<0.1"
+split-words = ">=0.1.2,<0.2.0"
+typer = ">=0.4.1,<0.5.0"
+
 [[package]]
 name = "jsonschema"
 version = "4.5.1"
@@ -1304,6 +1403,22 @@ urllib3 = ">=1.21.1,<1.27"
 socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"]
 use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
 
+[[package]]
+name = "rich"
+version = "12.4.3"
+description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
+category = "main"
+optional = false
+python-versions = ">=3.6.3,<4.0.0"
+
+[package.dependencies]
+commonmark = ">=0.9.0,<0.10.0"
+pygments = ">=2.6.0,<3.0.0"
+typing-extensions = {version = ">=4.0.0,<5.0", markers = "python_version < \"3.9\""}
+
+[package.extras]
+jupyter = ["ipywidgets (>=7.5.1,<8.0.0)"]
+
 [[package]]
 name = "scikit-learn"
 version = "1.1.1"
@@ -1427,6 +1542,14 @@ category = "main"
 optional = false
 python-versions = ">=3.6"
 
+[[package]]
+name = "split-words"
+version = "0.1.2"
+description = "Split German words"
+category = "main"
+optional = false
+python-versions = ">=3.8.3,<4.0.0"
+
 [[package]]
 name = "stack-data"
 version = "0.2.0"
@@ -1622,6 +1745,14 @@ dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)"]
 doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)"]
 test = ["shellingham (>=1.3.0,<2.0.0)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "coverage (>=5.2,<6.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "mypy (==0.910)", "black (>=22.3.0,<23.0.0)", "isort (>=5.0.6,<6.0.0)"]
 
+[[package]]
+name = "typing-extensions"
+version = "4.2.0"
+description = "Backported and Experimental Type Hints for Python 3.7+"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
 [[package]]
 name = "tzdata"
 version = "2022.1"
@@ -1735,9 +1866,17 @@ testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.8.3"
-content-hash = "6b30c86d829dc4b133c6fa3cc20ec4d76b702b8a1a0b44172b28e8aaa0851641"
+content-hash = "7fbe1cd54bf6ad1eb68f992dac0b0cd5a9095bfece8c31edb11e224e4e41d4f3"
 
 [metadata.files]
+about-time = [
+    {file = "about-time-3.1.1.tar.gz", hash = "sha256:586b329450c9387d1ae8c42d2db4f5b4c57a54508d0f1b7bb00322ffd5ce9f9b"},
+    {file = "about_time-3.1.1-py3-none-any.whl", hash = "sha256:96841beb3f9b5de1cbb323d2bdb0fa9abdecbc46f2d546b9b3c2483d23daa17a"},
+]
+alive-progress = [
+    {file = "alive-progress-2.4.1.tar.gz", hash = "sha256:089757c8197f27ad972ba27e1060f6db92368d83c736884e159034fd74865323"},
+    {file = "alive_progress-2.4.1-py3-none-any.whl", hash = "sha256:5503ffca0a0607d5f0d24d3b10a718fe50e375470fa07602b246333eb7ec88ee"},
+]
 altair = [
     {file = "altair-4.2.0-py3-none-any.whl", hash = "sha256:0c724848ae53410c13fa28be2b3b9a9dcb7b5caa1a70f7f217bd663bb419935a"},
     {file = "altair-4.2.0.tar.gz", hash = "sha256:d87d9372e63b48cd96b2a6415f0cf9457f50162ab79dc7a31cd7e024dd840026"},
@@ -1773,6 +1912,10 @@ argon2-cffi-bindings = [
     {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ed2937d286e2ad0cc79a7087d3c272832865f779430e0cc2b4f3718d3159b0cb"},
     {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:5e00316dabdaea0b2dd82d141cc66889ced0cdcbfa599e8b471cf22c620c329a"},
 ]
+aset2pairs = [
+    {file = "aset2pairs-0.1.0-py3-none-any.whl", hash = "sha256:a7137c7492566933198eebcef8df8c77ffda2f239f0865ae28c2afaf2a252550"},
+    {file = "aset2pairs-0.1.0.tar.gz", hash = "sha256:ee8d69f5ddce401f4999182678b108d9580edcc19374e44ed698c2171a17b483"},
+]
 asttokens = [
     {file = "asttokens-2.0.5-py2.py3-none-any.whl", hash = "sha256:0844691e88552595a6f4a4281a9f7f79b8dd45ca4ccea82e5e05b4bbdb76705c"},
     {file = "asttokens-2.0.5.tar.gz", hash = "sha256:9a54c114f02c7a9480d56550932546a3f1fe71d8a02f1bc7ccd0ee3ee35cf4d5"},
@@ -1925,6 +2068,10 @@ colorama = [
     {file = "colorama-0.4.4-py2.py3-none-any.whl", hash = "sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2"},
     {file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
 ]
+commonmark = [
+    {file = "commonmark-0.9.1-py2.py3-none-any.whl", hash = "sha256:da2f38c92590f83de410ba1a3cbceafbc74fee9def35f9251ba9a971d6d66fd9"},
+    {file = "commonmark-0.9.1.tar.gz", hash = "sha256:452f9dc859be7f06631ddcb328b6919c67984aca654e5fefb3914d54691aed60"},
+]
 debugpy = [
     {file = "debugpy-1.6.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:eb1946efac0c0c3d411cea0b5ac772fbde744109fd9520fb0c5a51979faf05ad"},
     {file = "debugpy-1.6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e3513399177dd37af4c1332df52da5da1d0c387e5927dc4c0709e26ee7302e8f"},
@@ -1953,6 +2100,10 @@ defusedxml = [
     {file = "defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61"},
     {file = "defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69"},
 ]
+dzbee = [
+    {file = "dzbee-0.1.1a2-py3-none-any.whl", hash = "sha256:fe1c4e80be236a66639dba2ed7f1c71497def05e9a6eea838264ea9d92543426"},
+    {file = "dzbee-0.1.1a2.tar.gz", hash = "sha256:24dadb5fa6606d4fd54d28eb34db2126ce078a4a8b5032090dba2856ed906091"},
+]
 entrypoints = [
     {file = "entrypoints-0.4-py3-none-any.whl", hash = "sha256:f174b5ff827504fd3cd97cc3f8649f3693f51538c7e4bdf3ef002c8429d42f9f"},
     {file = "entrypoints-0.4.tar.gz", hash = "sha256:b706eddaa9218a19ebcd67b56818f05bb27589b1ca9e8d797b74affad4ccacd4"},
@@ -1996,6 +2147,9 @@ gitpython = [
     {file = "GitPython-3.1.27-py3-none-any.whl", hash = "sha256:5b68b000463593e05ff2b261acff0ff0972df8ab1b70d3cdbd41b546c8b8fc3d"},
     {file = "GitPython-3.1.27.tar.gz", hash = "sha256:1c885ce809e8ba2d88a29befeb385fcea06338d3640712b59ca623c220bb5704"},
 ]
+grapheme = [
+    {file = "grapheme-0.6.0.tar.gz", hash = "sha256:44c2b9f21bbe77cfb05835fec230bd435954275267fea1858013b102f8603cca"},
+]
 icecream = [
     {file = "icecream-2.1.2-py2.py3-none-any.whl", hash = "sha256:04b9cea4d9931cf6960db0430ebf11fa34464ce7152e384ddf50f96d25b201b4"},
     {file = "icecream-2.1.2.tar.gz", hash = "sha256:09300b2d1c678712410cbd47c95198eb1b580f66f311a554ccd6b9e758ece0ee"},
@@ -2048,6 +2202,10 @@ joblib = [
     {file = "joblib-1.1.0-py2.py3-none-any.whl", hash = "sha256:f21f109b3c7ff9d95f8387f752d0d9c34a02aa2f7060c2135f465da0e5160ff6"},
     {file = "joblib-1.1.0.tar.gz", hash = "sha256:4158fcecd13733f8be669be0683b96ebdbbd38d23559f54dca7205aea1bf1e35"},
 ]
+json-de2zh = [
+    {file = "json_de2zh-0.1.1a0-py3-none-any.whl", hash = "sha256:ae20c3296912e8c9a013ed53ff361cc18e0f1524f2641fb86e2c4e65994dc199"},
+    {file = "json_de2zh-0.1.1a0.tar.gz", hash = "sha256:ff15c6418d52340d401dc69854c6d90b088aa5d535930c4d73ea4d0aca8161ca"},
+]
 jsonschema = [
     {file = "jsonschema-4.5.1-py3-none-any.whl", hash = "sha256:71b5e39324422543546572954ce71c67728922c104902cb7ce252e522235b33f"},
     {file = "jsonschema-4.5.1.tar.gz", hash = "sha256:7c6d882619340c3347a1bf7315e147e6d3dae439033ae6383d6acb908c101dfc"},
@@ -2657,6 +2815,10 @@ requests = [
     {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"},
     {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"},
 ]
+rich = [
+    {file = "rich-12.4.3-py3-none-any.whl", hash = "sha256:26ef784599a9ab905ade34ff28904e4fbe9bce16e02c33c78b0229551104c146"},
+    {file = "rich-12.4.3.tar.gz", hash = "sha256:e7550ca19aec51b216ae4c34bfce82e94a0c79bdbf95cafbf42f343d0fb3f45a"},
+]
 scikit-learn = [
     {file = "scikit-learn-1.1.1.tar.gz", hash = "sha256:3e77b71e8e644f86c8b5be7f1c285ef597de4c384961389ee3e9ca36c445b256"},
     {file = "scikit_learn-1.1.1-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:102f51797cd8944bf44a038d106848ddf2804f2c1edf7aea45fba81a4fdc4d80"},
@@ -2796,6 +2958,10 @@ soupsieve = [
     {file = "soupsieve-2.3.2.post1-py3-none-any.whl", hash = "sha256:3b2503d3c7084a42b1ebd08116e5f81aadfaea95863628c80a3b774a11b7c759"},
     {file = "soupsieve-2.3.2.post1.tar.gz", hash = "sha256:fc53893b3da2c33de295667a0e19f078c14bf86544af307354de5fcf12a3f30d"},
 ]
+split-words = [
+    {file = "split-words-0.1.2.tar.gz", hash = "sha256:4b8ed2bd86e266570e61c5e9ae210e7cf5e01b530e7dace2a047cd86af5276c9"},
+    {file = "split_words-0.1.2-py3-none-any.whl", hash = "sha256:5c7657f03fbdbe8ec731afff715e0779f754a01dbeac8ddc762ee2f2af6d4eb8"},
+]
 stack-data = [
     {file = "stack_data-0.2.0-py3-none-any.whl", hash = "sha256:999762f9c3132308789affa03e9271bbbe947bf78311851f4d485d8402ed858e"},
     {file = "stack_data-0.2.0.tar.gz", hash = "sha256:45692d41bd633a9503a5195552df22b583caf16f0b27c4e58c98d88c8b648e12"},
@@ -2895,6 +3061,10 @@ typer = [
     {file = "typer-0.4.1-py3-none-any.whl", hash = "sha256:e8467f0ebac0c81366c2168d6ad9f888efdfb6d4e1d3d5b4a004f46fa444b5c3"},
     {file = "typer-0.4.1.tar.gz", hash = "sha256:5646aef0d936b2c761a10393f0384ee6b5c7fe0bb3e5cd710b17134ca1d99cff"},
 ]
+typing-extensions = [
+    {file = "typing_extensions-4.2.0-py3-none-any.whl", hash = "sha256:6657594ee297170d19f67d55c05852a874e7eb634f4f753dbd667855e07c1708"},
+    {file = "typing_extensions-4.2.0.tar.gz", hash = "sha256:f1c24655a0da0d1b67f07e17a5e6b2a105894e6824b92096378bb3668ef02376"},
+]
 tzdata = [
     {file = "tzdata-2022.1-py2.py3-none-any.whl", hash = "sha256:238e70234214138ed7b4e8a0fab0e5e13872edab3be586ab8198c407620e2ab9"},
     {file = "tzdata-2022.1.tar.gz", hash = "sha256:8b536a8ec63dc0751342b3984193a3118f8fca2afe25752bb9b7fffd398552d3"},

pyproject.toml

@@ -17,6 +17,7 @@ streamlit-multipage = "^0.0.18"
 cchardet = "^2.1.7"
 streamlit-aggrid = "^0.2.3"
 ezbee = "0.1.0a3"
+dzbee = "^0.1.1-alpha.2"
 
 [tool.poe.executor]
 type = "poetry"

tests/test_litbee.py

@@ -1,7 +1,6 @@
 """Test litbee."""
 # pylint: disable=broad-except
-from litbee import __version__
-from litbee import litbee
+from litbee import __version__, litbee
 
 
 def test_version():