Update docs

docs/build/html/_sources/userguide-zh.rst.txt

@@ -9,7 +9,7 @@
 -  ``tf_type`` ``idf_type`` ``dl_type`` ``norm``: 一般无需理会这些参数。
 -  ``esp`` 和 ``min_samples`` 的建议值 -- ``esp`` (最小 ``epsilon``): 8-12, ``min_samples``: 4-8.
 
-   -   ``esp`` 设大些或 ``min_samples`` 设小些可以得到更多的对齐对但也会“误报对” (错误判断为对齐的对)。另一方面，``esp``  设小些或 ``min_samples`` 设大些则可能会错失一些“优质对”。
+   -   ``esp`` 设大些或 ``min_samples`` 设小些可以得到更多的对齐对但也会有更多“误报对” (错误判断为对齐的对)。另一方面，``esp``  设小些或 ``min_samples`` 设大些则会得到少一些对齐对因为可能错失了一些“优质对”。
 
 -  嫌图太小的话，可以右击拷出图的链接用浏览器独立访问拷出来的链接或右击存盘再用看图程序打开存盘的图文件。
 -   ``Flag``： ``radiobee`` 运行出错时可以点击 ``Flag`` 存下有关参数查看或通知开发者。

docs/build/html/searchindex.js

@@ -1 +1 @@
-Search.setIndex({docnames:["examples","index","intro","modules","radiobee","userguide","userguide-zh"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["examples.rst","index.rst","intro.rst","modules.rst","radiobee.rst","userguide.rst","userguide-zh.rst"],objects:{},objnames:{},objtypes:{},terms:{"12":[5,6],"3":2,"316287378":[5,6],"4":[5,6],"8":[5,6],"\u4e00\u822c\u65e0\u9700\u7406\u4f1a\u8fd9\u4e9b\u53c2\u6570":6,"\u4e86\u89e3\u8fd9\u4e9b\u5bf9\u9f50\u5de5\u5177":6,"\u4ee5\u540e\u53ef\u80fd\u4f1a\u652f\u6301":6,"\u4f18\u8d28\u5bf9":6,"\u4f7f\u7528\u8bf4\u660e":1,"\u53e6\u4e00\u65b9\u9762":6,"\u53ef\u4ee5\u4ee5\u540e\u4f1a\u652f\u6301":[],"\u53ef\u4ee5\u53f3\u51fb\u62f7\u51fa\u56fe\u7684\u94fe\u63a5\u7528\u6d4f\u89c8\u5668\u72ec\u7acb\u8bbf\u95ee\u62f7\u51fa\u6765\u7684\u94fe\u63a5\u6216\u53f3\u51fb\u5b58\u76d8\u518d\u7528\u770b\u56fe\u7a0b\u5e8f\u6253\u5f00\u5b58\u76d8\u7684\u56fe\u6587\u4ef6":6,"\u548c":6,"\u5acc\u56fe\u592a\u5c0f\u7684\u8bdd":6,"\u5b58\u4e0b\u6709\u5173\u53c2\u6570\u67e5\u770b\u6216\u901a\u77e5\u5f00\u53d1\u8005":6,"\u662f":6,"\u6700\u5c0f":6,"\u7684\u5b6a\u751f\u5144\u5f1f":6,"\u7684\u5efa\u8bae\u503c":6,"\u76ee\u524d\u4ec5\u652f\u6301\u4e2d\u82f1":6,"\u76ee\u524d\u4ec5\u652f\u6301\u7eaf\u6587\u672c\u6587\u4ef6\u4e0a\u8f7d":6,"\u7b2c\u4e8c\u6b21\u4e0a\u8f7d\u6587\u4ef6\u524d\u8bf7\u70b9\u51fb":6,"\u7b49":6,"\u7b49\u683c\u5f0f":6,"\u82f1\u4e2d\u5bf9\u9f50":6,"\u8bbe\u5927\u4e9b\u5219\u53ef\u80fd\u4f1a\u9519\u5931\u4e00\u4e9b":6,"\u8bbe\u5927\u4e9b\u6216":6,"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a":6,"\u8bbe\u5c0f\u4e9b\u6216":6,"\u8bef\u62a5\u5bf9":6,"\u8bf7\u52a0\u5165qq\u7fa4":6,"\u8fd0\u884c\u51fa\u9519\u65f6\u53ef\u4ee5\u70b9\u51fb":6,"\u9519\u8bef\u5224\u65ad\u4e3a\u5bf9\u9f50\u7684\u5bf9":6,"\u9519\u8bef\u5bf9":[],"do":5,"new":5,As:0,For:0,If:[2,5],On:5,The:2,To:5,about:5,ad:2,address:5,aim:2,align:[0,2,5,6],align_s:[1,3],align_text:[1,3],also:5,although:2,amend_avec:[1,3],an:2,app:[1,3],ar:[2,5],been:[0,2],better:5,browser:5,built:0,bumblebe:[5,6],can:[2,5],candid:5,cannot:0,cat:2,clear:[5,6],click:[0,5],cmat2tset:[1,3],co:0,contact:2,content:3,copi:5,csv:[5,6],current:2,de:2,develop:[2,5],dl_type:[5,6],docterm_scor:[1,3],docx:[5,6],download:0,dual:2,dualtext:2,e:2,ebook:2,educ:2,en2zh:[1,3],en2zh_token:[1,3],en:2,epsilon:[5,6],esp:[5,6],etc:[2,5],exampl:[1,2],fals:5,file2text:[1,3],file:5,files2df:[1,3],first:5,flag:[5,6],format:5,full:2,further:2,g:2,gen_aset:[1,3],gen_eps_minsampl:[1,3],gen_model:[1,3],gen_pset:[1,3],gen_row_align:[1,3],go:5,good:5,gradio:2,group:5,ha:[0,2],hand:5,have:5,help:2,here:2,how:1,html:[5,6],http:0,huggingfac:0,identifi:5,idf_typ:[5,6],imag:5,implement:2,index:1,inform:5,insert_spac:[1,3],instal:1,interfac:2,interpolate_pset:[1,3],introduct:1,ja:2,join:5,just:0,know:5,languag:2,larger:5,later:5,learn:2,limit:1,lists2cmat:[1,3],loadtext:[1,3],look:5,machin:2,mai:5,md:[5,6],mdx_e2c:[1,3],method:0,mikee:0,min_sampl:[5,6],minimum:5,miss:5,modul:[1,3],more:5,motiv:1,need:5,norm:[5,6],normal:5,now:0,one:0,onli:2,onlin:0,open:5,other:5,output:5,packag:[0,1,3],page:1,pair:[2,5],paragraph:2,particular:2,pdf:[5,6],permit:2,pip:0,pleas:5,plot_cmat:[1,3],plot_df:[1,3],posit:5,power:2,process_upload:[1,3],provid:2,publish:0,pure:5,pypi:0,python:2,qq:5,radiobe:[0,2,5,6],result:5,right:5,row:0,ru:2,save:5,search:1,seg_text:[1,3],select:5,sentenc:2,should:5,shuffle_s:[1,3],sibl:5,smaller:5,smatrix:[1,3],someth:5,space:0,srt:[5,6],submit:[0,5],submodul:[1,3],subsequ:5,suggest:[0,5],support:[2,5],tab:5,tabl:0,tend:5,term:2,testrun:0,text:[2,5],tf_type:[5,6],time:2,tmx:2,touch:5,translat:2,trim_df:[1,3],two:2,txt:[5,6],unless:5,upload:5,us:[0,1,2],usag:1,valu:5,version:0,wa:2,welcom:2,what:5,when:[2,5],willing:2,wrong:5,yet:0,you:[2,5],zh:2,zip:0},titles:["Examples","Welcome to radiobee\u2019s documentation!","Introduction","radiobee","radiobee package","How to use","\u4f7f\u7528\u8bf4\u660e"],titleterms:{"\u4f7f\u7528\u8bf4\u660e":6,align_s:4,align_text:4,amend_avec:4,app:4,cmat2tset:4,content:[1,4],docterm_scor:4,document:1,en2zh:4,en2zh_token:4,exampl:0,file2text:4,files2df:4,gen_aset:4,gen_eps_minsampl:4,gen_model:4,gen_pset:4,gen_row_align:4,how:5,indic:1,insert_spac:4,instal:0,interpolate_pset:4,introduct:2,limit:2,lists2cmat:4,loadtext:4,mdx_e2c:4,modul:4,motiv:2,packag:4,plot_cmat:4,plot_df:4,process_upload:4,radiobe:[1,3,4],s:1,seg_text:4,shuffle_s:4,smatrix:4,submodul:4,tabl:1,trim_df:4,us:5,usag:0,welcom:1}})
+Search.setIndex({docnames:["examples","index","intro","modules","radiobee","userguide","userguide-zh"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["examples.rst","index.rst","intro.rst","modules.rst","radiobee.rst","userguide.rst","userguide-zh.rst"],objects:{},objnames:{},objtypes:{},terms:{"12":[5,6],"3":2,"316287378":[5,6],"4":[5,6],"8":[5,6],"\u4e00\u822c\u65e0\u9700\u7406\u4f1a\u8fd9\u4e9b\u53c2\u6570":6,"\u4e86\u89e3\u8fd9\u4e9b\u5bf9\u9f50\u5de5\u5177":6,"\u4ee5\u540e\u53ef\u80fd\u4f1a\u652f\u6301":6,"\u4f18\u8d28\u5bf9":6,"\u4f7f\u7528\u8bf4\u660e":1,"\u53e6\u4e00\u65b9\u9762":6,"\u53ef\u4ee5\u4ee5\u540e\u4f1a\u652f\u6301":[],"\u53ef\u4ee5\u53f3\u51fb\u62f7\u51fa\u56fe\u7684\u94fe\u63a5\u7528\u6d4f\u89c8\u5668\u72ec\u7acb\u8bbf\u95ee\u62f7\u51fa\u6765\u7684\u94fe\u63a5\u6216\u53f3\u51fb\u5b58\u76d8\u518d\u7528\u770b\u56fe\u7a0b\u5e8f\u6253\u5f00\u5b58\u76d8\u7684\u56fe\u6587\u4ef6":6,"\u548c":6,"\u5acc\u56fe\u592a\u5c0f\u7684\u8bdd":6,"\u5b58\u4e0b\u6709\u5173\u53c2\u6570\u67e5\u770b\u6216\u901a\u77e5\u5f00\u53d1\u8005":6,"\u662f":6,"\u6700\u5c0f":6,"\u7684\u5b6a\u751f\u5144\u5f1f":6,"\u7684\u5efa\u8bae\u503c":6,"\u76ee\u524d\u4ec5\u652f\u6301\u4e2d\u82f1":6,"\u76ee\u524d\u4ec5\u652f\u6301\u7eaf\u6587\u672c\u6587\u4ef6\u4e0a\u8f7d":6,"\u7b2c\u4e8c\u6b21\u4e0a\u8f7d\u6587\u4ef6\u524d\u8bf7\u70b9\u51fb":6,"\u7b49":6,"\u7b49\u683c\u5f0f":6,"\u82f1\u4e2d\u5bf9\u9f50":6,"\u8bbe\u5927\u4e9b\u5219\u4f1a\u5f97\u5230\u5c11\u4e00\u4e9b\u5bf9\u9f50\u5bf9\u56e0\u4e3a\u53ef\u80fd\u9519\u5931\u4e86\u4e00\u4e9b":6,"\u8bbe\u5927\u4e9b\u5219\u53ef\u80fd\u4f1a\u9519\u5931\u4e00\u4e9b":[],"\u8bbe\u5927\u4e9b\u6216":6,"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a":[],"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a\u6709\u66f4\u591a":6,"\u8bbe\u5c0f\u4e9b\u6216":6,"\u8bef\u62a5\u5bf9":6,"\u8bf7\u52a0\u5165qq\u7fa4":6,"\u8fd0\u884c\u51fa\u9519\u65f6\u53ef\u4ee5\u70b9\u51fb":6,"\u9519\u8bef\u5224\u65ad\u4e3a\u5bf9\u9f50\u7684\u5bf9":6,"\u9519\u8bef\u5bf9":[],"do":5,"new":5,As:0,For:0,If:[2,5],On:5,The:2,To:5,about:5,ad:2,address:5,aim:2,align:[0,2,5,6],align_s:[1,3],align_text:[1,3],also:5,although:2,amend_avec:[1,3],an:2,app:[1,3],ar:[2,5],been:[0,2],better:5,browser:5,built:0,bumblebe:[5,6],can:[2,5],candid:5,cannot:0,cat:2,clear:[5,6],click:[0,5],cmat2tset:[1,3],co:0,contact:2,content:3,copi:5,csv:[5,6],current:2,de:2,develop:[2,5],dl_type:[5,6],docterm_scor:[1,3],docx:[5,6],download:0,dual:2,dualtext:2,e:2,ebook:2,educ:2,en2zh:[1,3],en2zh_token:[1,3],en:2,epsilon:[5,6],esp:[5,6],etc:[2,5],exampl:[1,2],fals:5,file2text:[1,3],file:5,files2df:[1,3],first:5,flag:[5,6],format:5,full:2,further:2,g:2,gen_aset:[1,3],gen_eps_minsampl:[1,3],gen_model:[1,3],gen_pset:[1,3],gen_row_align:[1,3],go:5,good:5,gradio:2,group:5,ha:[0,2],hand:5,have:5,help:2,here:2,how:1,html:[5,6],http:0,huggingfac:0,identifi:5,idf_typ:[5,6],imag:5,implement:2,index:1,inform:5,insert_spac:[1,3],instal:1,interfac:2,interpolate_pset:[1,3],introduct:1,ja:2,join:5,just:0,know:5,languag:2,larger:5,later:5,learn:2,limit:1,lists2cmat:[1,3],loadtext:[1,3],look:5,machin:2,mai:5,md:[5,6],mdx_e2c:[1,3],method:0,mikee:0,min_sampl:[5,6],minimum:5,miss:5,modul:[1,3],more:5,motiv:1,need:5,norm:[5,6],normal:5,now:0,one:0,onli:2,onlin:0,open:5,other:5,output:5,packag:[0,1,3],page:1,pair:[2,5],paragraph:2,particular:2,pdf:[5,6],permit:2,pip:0,pleas:5,plot_cmat:[1,3],plot_df:[1,3],posit:5,power:2,process_upload:[1,3],provid:2,publish:0,pure:5,pypi:0,python:2,qq:5,radiobe:[0,2,5,6],result:5,right:5,row:0,ru:2,save:5,search:1,seg_text:[1,3],select:5,sentenc:2,should:5,shuffle_s:[1,3],sibl:5,smaller:5,smatrix:[1,3],someth:5,space:0,srt:[5,6],submit:[0,5],submodul:[1,3],subsequ:5,suggest:[0,5],support:[2,5],tab:5,tabl:0,tend:5,term:2,testrun:0,text:[2,5],tf_type:[5,6],time:2,tmx:2,touch:5,translat:2,trim_df:[1,3],two:2,txt:[5,6],unless:5,upload:5,us:[0,1,2],usag:1,valu:5,version:0,wa:2,welcom:2,what:5,when:[2,5],willing:2,wrong:5,yet:0,you:[2,5],zh:2,zip:0},titles:["Examples","Welcome to radiobee\u2019s documentation!","Introduction","radiobee","radiobee package","How to use","\u4f7f\u7528\u8bf4\u660e"],titleterms:{"\u4f7f\u7528\u8bf4\u660e":6,align_s:4,align_text:4,amend_avec:4,app:4,cmat2tset:4,content:[1,4],docterm_scor:4,document:1,en2zh:4,en2zh_token:4,exampl:0,file2text:4,files2df:4,gen_aset:4,gen_eps_minsampl:4,gen_model:4,gen_pset:4,gen_row_align:4,how:5,indic:1,insert_spac:4,instal:0,interpolate_pset:4,introduct:2,limit:2,lists2cmat:4,loadtext:4,mdx_e2c:4,modul:4,motiv:2,packag:4,plot_cmat:4,plot_df:4,process_upload:4,radiobe:[1,3,4],s:1,seg_text:4,shuffle_s:4,smatrix:4,submodul:4,tabl:1,trim_df:4,us:5,usag:0,welcom:1}})

docs/build/html/userguide-zh.html

@@ -80,7 +80,7 @@
 <li><p><code class="docutils literal notranslate"><span class="pre">tf_type</span></code> <code class="docutils literal notranslate"><span class="pre">idf_type</span></code> <code class="docutils literal notranslate"><span class="pre">dl_type</span></code> <code class="docutils literal notranslate"><span class="pre">norm</span></code>: 一般无需理会这些参数。</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">esp</span></code> 和 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 的建议值 – <code class="docutils literal notranslate"><span class="pre">esp</span></code> (最小 <code class="docutils literal notranslate"><span class="pre">epsilon</span></code>): 8-12, <code class="docutils literal notranslate"><span class="pre">min_samples</span></code>: 4-8.</p>
 <ul>
-<li><p><code class="docutils literal notranslate"><span class="pre">esp</span></code> 设大些或 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 设小些可以得到更多的对齐对但也会“误报对” (错误判断为对齐的对)。另一方面，<code class="docutils literal notranslate"><span class="pre">esp</span></code>  设小些或 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 设大些则可能会错失一些“优质对”。</p></li>
+<li><p><code class="docutils literal notranslate"><span class="pre">esp</span></code> 设大些或 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 设小些可以得到更多的对齐对但也会有更多“误报对” (错误判断为对齐的对)。另一方面，<code class="docutils literal notranslate"><span class="pre">esp</span></code>  设小些或 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 设大些则会得到少一些对齐对因为可能错失了一些“优质对”。</p></li>
 </ul>
 </li>
 <li><p>嫌图太小的话，可以右击拷出图的链接用浏览器独立访问拷出来的链接或右击存盘再用看图程序打开存盘的图文件。</p></li>

docs/source/userguide-zh.rst

@@ -9,7 +9,7 @@
 -  ``tf_type`` ``idf_type`` ``dl_type`` ``norm``: 一般无需理会这些参数。
 -  ``esp`` 和 ``min_samples`` 的建议值 -- ``esp`` (最小 ``epsilon``): 8-12, ``min_samples``: 4-8.
 
-   -   ``esp`` 设大些或 ``min_samples`` 设小些可以得到更多的对齐对但也会“误报对” (错误判断为对齐的对)。另一方面，``esp``  设小些或 ``min_samples`` 设大些则可能会错失一些“优质对”。
+   -   ``esp`` 设大些或 ``min_samples`` 设小些可以得到更多的对齐对但也会有更多“误报对” (错误判断为对齐的对)。另一方面，``esp``  设小些或 ``min_samples`` 设大些则会得到少一些对齐对因为可能错失了一些“优质对”。
 
 -  嫌图太小的话，可以右击拷出图的链接用浏览器独立访问拷出来的链接或右击存盘再用看图程序打开存盘的图文件。
 -   ``Flag``： ``radiobee`` 运行出错时可以点击 ``Flag`` 存下有关参数查看或通知开发者。

radiobee/process_upload.py

@@ -42,7 +42,13 @@ def process_upload(upload: Union[tempfile._TemporaryFileWrapper, bytes]) -> str:
         logger.error("Unable to read data from %s, errors: %s", fpath, e)
         data = str(e).encode()
 
-    encoding = cchardet.detect(data).get("encoding", "utf8")
+    # no data, empty file, return ""
+    if not data:
+        logger.info("empty file: %s", upload.name)
+        return ""
+
+    encoding = cchardet.detect(data).get("encoding")
+
     if encoding is not None:
         try:
             text = fpath.read_text(encoding)
@@ -59,9 +65,11 @@ def process_upload(upload: Union[tempfile._TemporaryFileWrapper, bytes]) -> str:
 
     # TODO
 
-    # return f"{upload.name} {type(upload)}\n\n..."
-    # return f"{upload.name}\n..."
-    return f"{upload.name}"
+    _ = Path(upload.name)
+    msg = f"binary file: {_.stem[:-8]}{_.suffix}"
+    logger.warning("%s", msg)
+
+    return msg
 
 
 _ = '''  # colab gradio-file-inputs-upload.ipynb

tests/test_main_single_input.py

@@ -15,6 +15,7 @@ from radiobee.cmat2tset import cmat2tset
 
 file1loc = "data/test-dual.txt"
 file2loc = ""
+file2loc = "data/empty.txt"
 
 file1 = tempfile._TemporaryFileWrapper(open(file1loc, "rb"), file1loc)
 if file2loc: