PyPI - pyxllib - Versions diffs - 0.3.127__tar.gz → 0.3.129__tar.gz - Mend

pyxllib 0.3.127tar.gz → 0.3.129tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (357) hide show

{pyxllib-0.3.127/pyxllib.egg-info → pyxllib-0.3.129}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyxllib
-Version: 0.3.127
+Version: 0.3.129
 Summary: 厦门理工模式识别团队通用python代码工具库
 Home-page: https://github.com/XLPRUtils/pyxllib
 Author: code4101

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxllib/data/pglib.py RENAMED Viewed

@@ -194,7 +194,7 @@ WHERE {table_name}.{item_id_name} = cte.{item_id_name}"""
     @classmethod
     def cvt_type(cls, val):
         if isinstance(val, (dict, list)):
-            val = json.dumps(val, ensure_ascii=False)
+            val = json.dumps(val, ensure_ascii=False, default=str)
         # 注意list数组类型读、写都会自动适配py
         return val
@@ -781,27 +781,30 @@ class XlprDb(Connection):
         def pretty_val(v):
             return round_int(v) if v > 100 else round(v, 2)
-        chart = Line()
-        chart.set_title(title)
-        chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
-                                          # 'minInterval': 3600 * 1000 * 24,
-                                          'name': '时间', 'nameGap': 50, 'nameLocation': 'middle'})
-        chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
-        # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
-        chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
-        chart.options['grid'] = [{'top': 55 + len(all_users_usaged) * 4, 'containLabel': True}]
-        chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
-        chart.add_series(f'total{pretty_val(ls[0][1]):g}', to_list([x[1] for x in ls]), areaStyle={})
-        for user, usaged in all_users_usaged.most_common():
-            usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
-            chart.add_series(f'{user}{pretty_val(usaged):g}',
-                             to_list([x[2].get(user, 0) for x in ls]),
-                             areaStyle={}, stack='Total', emphasis={'focus': 'series'})
-        return '<body>' + chart.render_embed() + '</body>', sum(all_users_usaged.values())
-#   cdx_edit
+        try:
+            chart = Line()
+            chart.set_title(title)
+            chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
+                                              # 'minInterval': 3600 * 1000 * 24,
+                                              'name': '时间', 'nameGap': 50, 'nameLocation': 'middle'})
+            chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
+            # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
+            chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
+            chart.options['grid'] = [{'top': 55 + len(all_users_usaged) * 4, 'containLabel': True}]
+            chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
+            chart.add_series(f'total{pretty_val(ls[0][1]):g}', to_list([x[1] for x in ls]), areaStyle={})
+            for user, usaged in all_users_usaged.most_common():
+                usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
+                chart.add_series(f'{user}{pretty_val(usaged):g}',
+                                 to_list([x[2].get(user, 0) for x in ls]),
+                                 areaStyle={}, stack='Total', emphasis={'focus': 'series'})
+            return '<body>' + chart.render_embed() + '</body>', sum(all_users_usaged.values())
+        except Exception as e:
+            return str(e), 0
+    #   cdx_edit
     def _get_database_trace_total(self, title, yaxis_name, date_trunc, recent, link_name):
         ls = self.execute(textwrap.dedent(f"""\
             WITH cte1 AS(
@@ -817,7 +820,6 @@ class XlprDb(Connection):
             ORDER BY ttime"""), ((utc_now(8) - recent).isoformat(timespec='seconds'),)).fetchall()
         return self.database_create_stack_chart(title, ls, yaxis_name=yaxis_name)
     def _get_database_trace_per_host(self, db, title, yaxis_name, date_trunc, recent, link_name):
         ls = self.execute(textwrap.dedent(f"""\
             WITH cte1 AS (
@@ -860,20 +862,20 @@ class XlprDb(Connection):
                 if k == '_total':
                     continue
                 all_database_usaged[k] += v * hours
         for i, x in enumerate(ls):
             ct = Counter()
             for k, v in x[1].items():
                 ct[k] += v
             ls[i] = (x[0], ct, int(x[2]))
         # 2 转图表可视化
         def to_list(values):
             return [(x[0], v) for x, v in zip(ls, values)]
         def pretty_val(v):
             return round_int(v) if v > 100 else round(v, 2)
         chart = Line()
         chart.set_title(title)
         chart.options['xAxis'][0].update({'min': ls[0][0], 'type': 'time',
@@ -882,51 +884,52 @@ class XlprDb(Connection):
         chart.options['yAxis'][0].update({'name': yaxis_name, 'nameGap': 50, 'nameLocation': 'middle'})
         # 目前是比较暴力的方法调整排版，后续要研究是不是能更自动灵活些
         chart.options['legend'][0].update({'top': '6%', 'icon': 'pin'})
-        chart.options['grid'] = [{'top': 55 + len(all_database_usaged) * 4 , 'containLabel': True}]
+        chart.options['grid'] = [{'top': 55 + len(all_database_usaged) * 4, 'containLabel': True}]
         chart.options['tooltip'].opts.update({'axisPointer': {'type': 'cross'}, 'trigger': 'item'})
-        chart.add_series(f'total {pretty_val(ls[0][2]/1024/1024/1024):g}', to_list([x[2]/1024/1024/1024 for x in ls]), areaStyle={})
+        #chart.add_series(f'total {pretty_val(ls[0][2] / 1024 / 1024 / 1024):g}',
+        #                 to_list([x[2] / 1024 / 1024 / 1024 for x in ls]), areaStyle={})
         for database, usaged in all_database_usaged.most_common():
             usaged = usaged / ((ls[-1][0] - ls[0][0]).total_seconds() / 3600 + 1e-9)
-            chart.add_series(f'{database} {pretty_val(usaged/1024/1024/1024):g}',
-                             to_list([x[1].get(database, 0)/1024/1024/1024 for x in ls]),
+            chart.add_series(f'{database} {pretty_val(usaged / 1024 / 1024 / 1024):g}',
+                             to_list([x[1].get(database, 0) / 1024 / 1024 / 1024 for x in ls]),
                              areaStyle={}, stack='Total', emphasis={'focus': 'series'})
         return '<body>' + chart.render_embed() + '</body>'
-    def dbview_xldb1_memory(self,recent=datetime.timedelta(days=30), date_trunc='hour'):
+    def dbview_xldb1_memory(self, recent=datetime.timedelta(days=180), date_trunc='day'):
         from pyxllib.data.echarts import render_echart_html
-        db_list = ['st', 'xlpr', 'stdata', 'kq5034', 'ckz']
+        db_list = ['stdata', 'xlpr', 'st', 'ckz']
         args = ['数据库大小(GB)', date_trunc, recent, 'xldb1']
         htmltexts = []
-        res = self._get_database_trace_total('XLDB1数据库使用近况', *args)
+        res = self._get_database_trace_total('xldb1数据库使用近况', *args)
         htmltexts.append(res)
         data_stats = []
-        for idx,db in enumerate(db_list,start=1):
-            data_stats.append(self._get_database_trace_per_host(db,f'{db}', *args))
+        for idx, db in enumerate(db_list, start=1):
+            data_stats.append(self._get_database_trace_per_host(db, f'{db}', *args))
         htmltexts += data_stats
         self.commit()
         h = render_echart_html('database_cdx', body='<br/>'.join(htmltexts))
         return h
-    def dbview_xldb2_memory(self, recent=datetime.timedelta(days=30), date_trunc='hour'):
+    def dbview_xldb2_memory(self, recent=datetime.timedelta(days=180), date_trunc='day'):
         from pyxllib.data.echarts import render_echart_html
-        db_list = ['st', 'ragdata']
+        db_list = ['ragdata', 'kq5034']
         args = ['数据库大小(GB)', date_trunc, recent, 'xldb2']
         htmltexts = []
-        res = self._get_database_trace_total('XLDB2数据库使用近况', *args)
+        res = self._get_database_trace_total('xldb2数据库使用近况', *args)
         htmltexts.append(res)
         data_stats = []
         for idx, db in enumerate(db_list, start=1):
             data_stats.append(self._get_database_trace_per_host(db, f'{db}', *args))
         htmltexts += data_stats
         self.commit()
         h = render_echart_html('database_cdx', body='<br/>'.join(htmltexts))
         return h
@@ -977,7 +980,7 @@ class XlprDb(Connection):
         h = render_echart_html('cpu_memory', body='<br/>'.join(htmltexts))
         return h
-    def dbview_disk_memory(self, recent=datetime.timedelta(days=30), date_trunc='day'):
+    def dbview_disk_memory(self, recent=datetime.timedelta(days=360), date_trunc='day'):
         """ 查看disk硬盘使用近况
         """
         from pyxllib.data.echarts import render_echart_html

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxllib/ext/yuquelib.py RENAMED Viewed

@@ -20,10 +20,10 @@ class Yuque:
     语雀请求限制：每小时最多 5000 次请求，每秒最多 100 次请求
     """
-    def __init__(self, token, user_id=None):
+    def __init__(self, token=None, user_id=None):
         self.base_url = "https://www.yuque.com/api/v2"
         self.headers = {
-            "X-Auth-Token": token,
+            "X-Auth-Token": token or os.environ.get('YUQUE_TOKEN'),
             "Content-Type": "application/json"
         }
         self._user_id = user_id
@@ -197,7 +197,7 @@ class Yuque:
         elif return_mode == 'md':
             return res['data']['body']
         elif return_mode == 'title_and_md':
-            return f'文章标题：{res["data"]["title"]}\n\n{res["data"]["body"]}'
+            return res["data"]["title"], res["data"]["body"]
     def export_markdown(self, url, output_dir=None, post_mode=1):
         """ 导出md格式文件

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxllib/file/xlsxlib.py RENAMED Viewed

@@ -3018,12 +3018,51 @@ def extract_workbook_summary3(file_path, summary_limit_len=4000, **kwargs):
     return data
+def summary2_add_enums(summary2, enum_values):
+    # 1 预备
+    if enum_values is True:
+        enum_values = (20, 10)
+    max_len, max_num = enum_values
+    # 2 枚举值
+    for sheet in summary2['sheets']:
+        # 2.1 遍历计数
+        cols = defaultdict(Counter)
+        for addr, val in sheet['cells'].items():
+            n = len(str(val))
+            if not n or n > max_len:
+                continue
+            col = re.match(r'[A-Z]+', addr).group()
+            cols[col][val] += 1
+        # 2.2 添加枚举值列
+        enums = {}
+        keys = sorted(cols.keys(), key=column_index_from_string)
+        for k in keys:
+            ct = cols[k]
+            if len(ct) > max_num:
+                continue
+            vals = ct.most_common()
+            if vals[0][1] == 1:  # 都只出现了一次，也不认为是枚举值，跳过。或者是小数据表，一般也能全量展示。
+                continue
+            enums[k] = [v for v, _ in vals]
+        # 2.3 保存
+        if enums:
+            sheet['enums'] = enums
+            # enums2 = json.dumps(enums, ensure_ascii=False, default=str)
+            # sheet['enums'] = json.loads(enums2)
+    return summary2
 def extract_workbook_summary3b(file_path,
                                summary_limit_len=4000,
                                timeout_seconds=10,
                                return_mode=0,
                                debug=False,
                                len_mode=0,
+                               enum_values=False,
                                **kwargs):
     """
@@ -3036,6 +3075,9 @@ def extract_workbook_summary3b(file_path,
     :param len_mode:
         0, 使用len作为token长度评估
         1, 使用模型评估实际token长度
+    :param enum_values: 是否展示每列枚举值
+        False, 默认不展示
+        True, 展示，并且默认参数 (20, 10) 表示长度超过20的丢弃，只保留枚举类型不超过10种值的列
     :param kwargs: 其他是summary2读取文件的时候的参数，其实都不太关键，一般不用特地设置
     """
     res = {}
@@ -3056,7 +3098,10 @@ def extract_workbook_summary3b(file_path,
             res, load_time = extract_workbook_summary2(file_path, mode=1, return_mode=1, **kwargs)
             # res = convert_to_json_compatible(res)
             summary2_res = copy.deepcopy(res)
+            if enum_values:
+                res = summary2_add_enums(res, enum_values)
             summary2_time = time.time() - start_time - load_time
             start_time = time.time()
             if len_mode == 1:
                 res = WorkbookSummary3plus.summary2_to_summary3b(res, summary_limit_len)

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxllib/prog/pupil.py RENAMED Viewed

@@ -1223,7 +1223,6 @@ def support_multi_processes(default_processes=1):
                         cmds.append(f'--{k}')  # 添加关键字参数的键
                         cmds.append(str(v))  # 添加关键字参数的值
-                    mpl.add_process_python_module()
                     mpl.add_process_python(sys.argv[0], cmds, shell=shell)
                 mpl.run_endless()

{pyxllib-0.3.127 → pyxllib-0.3.129/pyxllib.egg-info}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyxllib
-Version: 0.3.127
+Version: 0.3.129
 Summary: 厦门理工模式识别团队通用python代码工具库
 Home-page: https://github.com/XLPRUtils/pyxllib
 Author: code4101

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxllib.egg-info/requires.txt RENAMED Viewed

@@ -23,31 +23,32 @@ pandas>=0.23.4
 pillow
 [xlai]
-pillow
+visdom
 opsdroid-get-image-size
 pynvml
-visdom
+pillow
 opencv-python
 [xlall]
-pillow
-flask-jwt-extended
-flask
-fastapi
-opsdroid-get-image-size
-html2text
-ujson
+zhconv
 arts
 uvicorn
-flask-wtf
-zhconv
+html2text
+openai2
+opsdroid-get-image-size
+fastapi
+flask-restful
+flask-jwt-extended
 sentencepiece
-flask-cors
+ujson
+pillow
+flask
 xlrd
-flask-restful
+flask-wtf
+flask-cors
 opencv-python
 [xlcv]
-opencv-python
 opsdroid-get-image-size
 pillow
+opencv-python

{pyxllib-0.3.127 → pyxllib-0.3.129}/pyxlpr/openai2/_core/chat.py RENAMED Viewed

@@ -15,6 +15,7 @@ import logging
 from unittest.mock import MagicMock
 import math
 from types import SimpleNamespace
+from typing import Union
 import requests
 from loguru import logger as loguru_logger
@@ -132,11 +133,11 @@ class Chat:
     recently_request_data: dict  # 最近一次请求所用的参数
     default_api_key = None
-    default_base_url = "https://console.chatdata.online/v1"
+    default_base_url = "https://platform.llmprovider.ai/v1"
     def __init__(self,
                  # kwargs
-                 api_key: str | AKPool = None,
+                 api_key: Union[str, AKPool] = None,
                  base_url: str = None,  # base_url 参数用于修改基础URL
                  timeout=None,
                  max_retries=None,
@@ -145,7 +146,7 @@ class Chat:
                  model: Literal["gpt-4-1106-preview", "gpt-4-vision-preview",
                  "gpt-4", "gpt-4-0314", "gpt-4-0613",
                  "gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613", "gpt-3.5-turbo",
-                 "gpt-4o", "gpt-4-turbo"] = "gpt-3.5-turbo",
+                 "gpt-4o", "gpt-4-turbo"] = "gpt-4o-mini",
                  # Chat
                  msg_max_count: int = None,
                  # kwargs
@@ -176,7 +177,7 @@ class Chat:
     def __1_原作者提供功能(self):
         pass
-    def reset_api_key(self, api_key: str | AKPool):
+    def reset_api_key(self, api_key: Union[str, AKPool]):
         if isinstance(api_key, AKPool):
             self._akpool = api_key
         else:
@@ -283,7 +284,7 @@ class Chat:
     def fetch_messages(self):
         return list(self._messages)
-    def add_dialogs(self, *ms: dict | system_msg | user_msg | assistant_msg):
+    def add_dialogs(self, *ms: Union[dict, system_msg, user_msg, assistant_msg]):
         '''
         添加历史对话
         '''
@@ -505,7 +506,7 @@ class Chat2:
                  gizmo_id=None,
                  *,
                  base_url=None,
-                 model='gpt-4o'):
+                 model='gpt-4o-mini'):
         """
         :param gizmo_id: gpts的id，比如 https://chatgpt.com/g/g-ABCD1234-ce-shi。则id就是"g-ABCD1234"
             后面的gpts的名称变了没关系，前面前缀的id不要变就行
@@ -563,7 +564,7 @@ class Chat2:
             url = f"{self.base_url}/chat/all-tools"
         headers = self.headers.copy()
-        headers['Content-Type'] = 'application/json'
+        # headers['Content-Type'] = 'application/json'
         # 2 api初步配置
         payload = self.session_state.copy()
@@ -586,7 +587,8 @@ class Chat2:
                 self._upload_image(image, parent_payload=payload)
         # 5 请求
-        resp = requests.post(url, headers=headers, data=json.dumps(payload))
+        # resp = requests.post(url, headers=headers, data=json.dumps(payload))
+        resp = requests.post(url, headers=headers, json=payload)  # 我觉得应该可以改这样调用，但还没测试
         resp_json = resp.json()
         # 6 保存状态
@@ -597,6 +599,43 @@ class Chat2:
         return '\n\n'.join(resp_json['contents'][-1]['message']['content']['parts'])
+class DifyChat:
+    default_base_url = 'http://localhost'
+    def __init__(self, app_key, *,
+                 conversation_id=None,
+                 user=None,
+                 base_url=None):
+        self.app_key = app_key
+        self.base_url = base_url or self.default_base_url
+        self.headers = {
+            'Authorization': f'Bearer {self.app_key}',
+        }
+        self.conversation_state = {
+            'inputs': {},
+            # 'response_mode': 'streaming',
+            'conversation_id': conversation_id or '',
+            'user': user or 'code4101',
+        }
+    def query(self, query, *, files=None, images=None):
+        """ files、images等后期再加
+        """
+        # 1 请求
+        payload = self.conversation_state.copy()
+        payload['query'] = query
+        resp = requests.post(f'{self.base_url}/v1/chat-messages',
+                             headers=self.headers, json=payload)
+        resp_json = resp.json()  # 如果需要可以打印这个字典看结构
+        # 2 保存状态
+        self.conversation_state['conversation_id'] = resp_json.get('conversation_id', '')
+        return resp_json['answer']
 def __2_信息摘要():
     pass
@@ -697,7 +736,7 @@ class CompressContent:
               expect_len=None,
               max_round=-1,
               text_spliter=None,
-              model='gpt-3.5-turbo',
+              model='gpt-4o-mini',
               soft_merge_prompt=None,
               calc_len=None,
               logger=None,

{pyxllib-0.3.127 → pyxllib-0.3.129}/setup.py RENAMED Viewed

@@ -41,14 +41,16 @@ flask-jwt-extended
 fastapi
 arts
 uvicorn
+openai2
 """
 # pywin32
+# openai2里有个import arts的东西，这个arts才是作者原本的库
 _dir = Path(__file__).parent
 setup(
     name='pyxllib',  # pip 安装时用的名字
-    version='0.3.127',  # 当前版本，每次更新上传到pypi都需要修改; 第4位版本号一般是修紧急bug
+    version='0.3.129',  # 当前版本，每次更新上传到pypi都需要修改; 第4位版本号一般是修紧急bug
     author='code4101',
     author_email='877362867@qq.com',
     url='https://github.com/XLPRUtils/pyxllib',