append

code/pep-stats-report/Dockerfile

@@ -5,7 +5,7 @@ WORKDIR /app
 COPY . .
 
 RUN pip install --upgrade pip -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com && \
-    pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com && \
+    pip install -r requirements_linux.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com && \
     cp SimHei.ttf /usr/local/lib/python3.8/site-packages/matplotlib/mpl-data/fonts/ttf && \
     pyinstaller -F main.py --distpath=. 
 
@@ -13,6 +13,13 @@ FROM debian:11-slim
 
 WORKDIR /app
 
-COPY --from=python_base /app/main /app/config.ini ./
+COPY --from=python_base /app/main /app/config.ini /app/SimHei.ttf ./
+
+RUN cp -a /etc/apt/sources.list /etc/apt/sources.list.bak && \
+    sed -i "s@http://deb.debian.org@http://mirrors.aliyun.com@g" /etc/apt/sources.list && \
+    sed -i "s@http://security.debian.org@http://mirrors.aliyun.com@g" /etc/apt/sources.list
+
+RUN apt-get update && apt-get install libreoffice -y && \
+    cp SimHei.ttf /usr/share/fonts/
 
 CMD ["./main"]

code/pep-stats-report/app/db_helper.py

@@ -1,5 +1,5 @@
 def querystring_user_procinst_duration(start, end, except_senior, department):
-    filter_user = "and u.name not in ('刘文峰', '金亮', '姜珍', '余莎莎', '张阳根', '唐国华', '刘国勇', '刘会连', '肖琥')" if except_senior else ""
+    filter_user = "and u.name not in ('刘文峰', '金亮', '姜珍', '余莎莎', '张阳根', '唐国华', '刘国勇', '刘会连', '肖琥', '邱峰')" if except_senior else ""
     filter_department = "and department_name='{}'".format(department) if department else ""
     return '''
 select department_name,
@@ -34,9 +34,6 @@ group by department_name, user_name, procinst_id
 
 def querystring_senior_procinst_duration(start, end):
     return '''
-SELECT user_name,
-     ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
-from (
 select user_name,
        procinst_id,
        sum(duration_in_minutes) as procinst_duration_in_minutes
@@ -56,11 +53,9 @@ from (
   inner join workflow_process as wp on wpv.process_id=wp.id
   inner join user as u on wpa.deal_user_id=u.id
   where wpa.end_time >='{}' and wpa.end_time < '{}' and wp.deleted=false and wp.is_enable=true and u.delete=0 and u.state=1 and u.active_status=1
-    and u.name in ('刘文峰', '金亮', '姜珍', '余莎莎', '张阳根', '唐国华', '刘国勇', '刘会连', '肖琥')
+    and u.name in ('刘文峰', '金亮', '姜珍', '余莎莎', '张阳根', '唐国华', '刘国勇', '刘会连', '肖琥', '邱峰')
 ) as r
 group by user_name, procinst_id
-) as r2
-GROUP by r2.user_name
     '''.format(start, end)
 
 
@@ -139,14 +134,22 @@ order by procinst_duration_in_hours_by_department DESC
 def querystring_procinst_duration_by_senior(start, end):
     return '''
 SELECT ROUND(AVG(procinst_duration_in_hours_by_user), 2) as procinst_duration_in_hours_by_department
-from ({}) as r3
+from (
+    SELECT user_name,
+           ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
+    from ({}) as r2
+    GROUP by r2.user_name
+) as r3
     '''.format(querystring_senior_procinst_duration(start, end))
 
 
 # 用户单流程处理耗时（高管）
 def querystring_procinst_duration_by_user_senior(start, end):
     return '''
-{}
+SELECT user_name,
+       ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
+from ({}) as r2
+GROUP by r2.user_name
 order by procinst_duration_in_hours_by_user DESC
     '''.format(querystring_senior_procinst_duration(start, end))
 
@@ -154,7 +157,12 @@ order by procinst_duration_in_hours_by_user DESC
 # 各部门耗时较长用户（高管）
 def querystring_user_gt_senior_avg(start, end, avg):
     return '''
-SELECT * from ({}) as r3
+SELECT * from (
+    SELECT user_name,
+           ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
+    from ({}) as r2
+    GROUP by r2.user_name
+) as r3
 WHERE r3.procinst_duration_in_hours_by_user > {}
 order by procinst_duration_in_hours_by_user DESC
     '''.format(querystring_senior_procinst_duration(start, end), avg)
@@ -178,8 +186,28 @@ order by procinst_duration_in_hours_by_user desc
 def querystring_procinst_duration_by_user(start, end, department):
     return """
 SELECT user_name,
-     ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
+       ROUND(AVG(procinst_duration_in_minutes) /60, 2) as procinst_duration_in_hours_by_user
 from ({}) as r2
 group by r2.user_name
 order by procinst_duration_in_hours_by_user DESC
     """.format(querystring_user_procinst_duration(start, end, True, department))
+
+
+# 按部门统计用户处理流程数量
+def querystring_procinst_count_by_user(start, end, department):
+    return '''
+SELECT user_name,
+       COUNT(*) as procinst_count_by_user
+from ({}) as r2
+group by r2.user_name
+    '''.format(querystring_user_procinst_duration(start, end, True, department))
+
+
+# 用户处理流程数量（高管）
+def querystring_procinst_count_by_senior(start, end):
+    return '''
+SELECT user_name,
+       COUNT(*) as procinst_count_by_user
+from ({}) as r2
+group by r2.user_name
+    '''.format(querystring_senior_procinst_duration(start, end))

code/pep-stats-report/app/image_helper.py

@@ -0,0 +1,110 @@
+import platform
+import os
+import fitz  # pip install PyMuPDF
+from PIL import Image
+import shutil
+import logging
+
+
+# 将word文件转换成pdf文件
+def word2pdf(word_file):
+    from win32com import client  # pip install pywin32
+
+    # 获取word格式处理对象
+    word = client.Dispatch('Word.Application')
+    # 以Doc对象打开文件
+    doc_ = word.Documents.Open(word_file)
+    # 另存为pdf文件
+    pdf_file = word_file.replace(os.path.basename(word_file).split('.')[1], "pdf")
+    doc_.SaveAs(pdf_file, FileFormat=17)
+    logging.info(f'{word_file} ----转pdf成功')
+    # 关闭doc对象
+    doc_.Close()
+    # 退出word对象
+    word.Quit()
+    return pdf_file
+
+
+# 将word文件转换成pdf文件（Linux）
+def word2pdf_linux(word_file):
+    word_path = os.path.dirname(word_file)
+    os.system(f"libreoffice --headless --language=zh-CN --convert-to pdf {word_file} --outdir {word_path}")
+    logging.info(f'{word_file} ----转pdf成功')
+    pdf_file = word_file.replace(os.path.basename(word_file).split('.')[1], "pdf")
+    return pdf_file
+
+
+# pdf转图片
+def pdf2png(pdf_file):
+    image_path = os.path.abspath(f'{os.path.dirname(pdf_file)}/tmp_pdf2png')
+    try:
+        # 创建一个空白图片，用于拼接内容
+        width, height = 0, 0
+        images = []
+
+        pdf_doc = fitz.open(pdf_file)
+        for pg in range(pdf_doc.page_count):
+            page = pdf_doc[pg]
+            rotate = int(0)
+            # 每个尺寸的缩放系数为1.3，这将为我们生成分辨率提高2.6的图像。
+            # 此处若是不做设置，默认图片大小为：792X612, dpi=96
+            zoom_x = 1.33333333  # (1.33333333-->1056x816)   (2-->1584x1224)
+            zoom_y = 1.33333333
+            mat = fitz.Matrix(zoom_x, zoom_y).prerotate(rotate)
+            pix = page.get_pixmap(matrix=mat, alpha=False)
+
+            if not os.path.exists(image_path):  # 判断存放图片的文件夹是否存在
+                os.makedirs(image_path)  # 若图片文件夹不存在就创建
+            pix.save(image_path + '/' + 'tmp%s.png' % pg)  # 将图片写入指定的文件夹内
+
+            img = Image.open(image_path + '/' + 'tmp%s.png' % pg)
+            img_width, img_height = img.size
+
+            # 更新拼接图片的宽度和高度
+            width = max(width, img_width)
+            height += img_height
+
+            # 添加图片到拼接列表
+            images.append(img)
+
+        # 创建一个空白长图
+        long_image = Image.new('RGB', (width, height), (255, 255, 255))
+        y_offset = 0
+
+        # 将每张图片拼接到长图中
+        for img in images:
+            long_image.paste(img, (0, y_offset))
+            y_offset += img.height
+
+        # 保存拼接后的长图
+        png_file = pdf_file.replace(os.path.basename(pdf_file).split('.')[1], "png")
+        long_image.save(png_file)
+
+        # 删除中间临时保存的图片
+        shutil.rmtree(image_path)
+    except IOError as error:
+        logging.error('pdf转png失败')
+        raise error
+    else:
+        logging.info("pdf转png成功")
+        return png_file
+
+
+def word_to_long_image(word_file_path):
+    try:
+        _file = os.path.abspath(word_file_path)  # os.path.abspath('input.docx')
+
+        if platform.system().lower() == 'windows':
+            pdf_file = word2pdf(_file)
+        else:
+            pdf_file = word2pdf_linux(_file)
+
+        png_file = pdf2png(pdf_file)
+
+        # 删除中间保存的pdf文件
+        os.remove(pdf_file)
+
+        return png_file
+    except Exception as error:
+        logging.error('word转长图出错：{}'.format(error))
+        raise error

code/pep-stats-report/config.ini

@@ -3,7 +3,7 @@ host = 10.8.30.161
 port = 30900
 username = default
 password =
-database = pepca_m
+database = pepca9
 
 [qiniu]
 access-key=5XrM4wEB9YU6RQwT64sPzzE6cYFKZgssdP5Kj3uu

code/pep-stats-report/main.py

@@ -7,7 +7,8 @@ from docx.shared import Inches, Pt, RGBColor
 from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_LINE_SPACING
 from docx.oxml.ns import qn
 import matplotlib.pyplot as plt
-from app import db_helper
+import numpy as np
+from app import db_helper, image_helper
 import qiniu
 import logging
 
@@ -107,6 +108,43 @@ def create_bar_chart(doc, x, y, mean, title, filename):
     r.add_picture('{}/{}'.format(REPORT_DIR, filename), width=Inches(6))
 
 
+def create_bar_twinx_chart(doc, x, y1, y2, mean, title, filename):
+    plt.rcParams["font.sans-serif"] = ["SimHei"]  # 设置字体
+    plt.rcParams["axes.unicode_minus"] = False  # 正常显示负号
+
+    x_range = np.arange(len(x))
+
+    width = 0.25  # the width of the bars
+
+    fig, ax1 = plt.subplots()
+    ax1.set_ylabel('耗时')
+    rects = ax1.bar(x_range, y1, width, color=(31 / 255, 168 / 255, 201 / 255), label='耗时')
+    ax1.bar_label(rects, padding=3)
+    ax1.set_xticks(x_range + width / 2, x)
+    # 设置x轴标签旋转角度
+    plt.xticks(rotation=-30, ha='left')
+    # 绘制均值线
+    plt.axhline(mean, linestyle='dashed', color='#FF8C00', label=f'均值：{mean}')
+
+    ax2 = ax1.twinx()  # instantiate a second axes that shares the same x-axis
+
+    ax2.set_ylabel('流程数')
+    rects = ax2.bar(x_range + width, y2, width, color='#5AC189', label='流程数')
+    ax2.bar_label(rects, padding=3)
+
+    plt.title(title)
+    fig.legend(loc='upper right', ncols=1, bbox_to_anchor=(1, 1), bbox_transform=ax1.transAxes)
+    fig.tight_layout()  # otherwise the right y-label is slightly clipped
+    # 保存图形
+    plt.savefig('{}/{}'.format(REPORT_DIR, filename))
+    plt.close()
+    # 插入图形到 Word 文档中
+    p = doc.add_paragraph()
+    p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
+    r = p.add_run()
+    r.add_picture('{}/{}'.format(REPORT_DIR, filename), width=Inches(6))
+
+
 def add_section(doc, rank, department, d_elapse):
     h = doc.add_heading(level=2)
     r = h.add_run('{}. {}'.format(rank, department))
@@ -124,6 +162,12 @@ def add_section(doc, rank, department, d_elapse):
         ) if department == '高管' else db_helper.querystring_procinst_duration_by_user(
             start_time, end_time, department)
         procinst_duration_by_user = client.execute(qs)
+
+        qs = db_helper.querystring_procinst_count_by_senior(
+            start_time, end_time
+        ) if department == '高管' else db_helper.querystring_procinst_count_by_user(
+            start_time, end_time, department)
+        procinst_count_by_user = client.execute(qs)
     except Exception as error:
         print('数据库查询错误：', error)
         logging.error('数据库查询错误：{}'.format(error))
@@ -149,11 +193,20 @@ def add_section(doc, rank, department, d_elapse):
     set_paragraph_format(p)
 
     x = []
-    y = []
+    y1 = []
+    y2 = []
+
     for user, elapse in procinst_duration_by_user:
         x.append(user)
-        y.append(elapse)
+        y1.append(elapse)
-    create_bar_chart(doc, x, y, d_elapse, "个人流程处理平均耗时", "{}-流程处理平均耗时.png".format(department))
+
+    for name in x:
+        for user, count in procinst_count_by_user:
+            if user == name:
+                y2.append(count)
+                break
+
+    create_bar_twinx_chart(doc, x, y1, y2, d_elapse, "个人流程处理平均耗时", "{}-流程处理平均耗时.png".format(department))
     caption = doc.add_paragraph('图 2-{} {}个人处理流程平均耗时'.format(rank, department))
     caption.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
 
@@ -193,7 +246,7 @@ def add_chapter_1(doc):
         logging.error('数据库查询错误：{}'.format(error))
         raise RuntimeError('数据库查询错误：', error)
 
-    if procinst_duration_by_senior > procinst_duration_by_company:
+    if procinst_duration_by_senior is not None and procinst_duration_by_senior > procinst_duration_by_company:
         department_count_gt_avg += 1
 
     p = doc.add_paragraph()
@@ -289,12 +342,17 @@ def generate_word_report():
     set_paragraph_format(p_last)
 
     # 保存文档
-    report_path = '{}/项企流程效能分析结果公示（全员）-{}年{}月.docx'.format(REPORT_DIR, last_year, last_month)
+    report_file_name = '项企流程效能分析结果公示（全员）-{}年{}月.docx'.format(last_year, last_month)
-    doc.save(report_path)
+    report_file = f'{REPORT_DIR}/{report_file_name}'
-    logging.info('本地报表创建成功：{}'.format(report_path))
+    doc.save(report_file)
+    logging.info('本地报表创建成功：{}'.format(report_file))
+
+    # 将文档转换为图片
+    png_file = image_helper.word_to_long_image(report_file)
 
     # 上传七牛云
-    upload_to_qiniu('项企流程效能分析结果公示（全员）-{}年{}月.docx'.format(last_year, last_month))
+    upload_to_qiniu(report_file_name)
+    upload_to_qiniu(os.path.basename(png_file))
 
 
 def create_clickhouse_client():
@@ -343,7 +401,7 @@ if __name__ == '__main__':
         procinst_duration_by_senior = client.execute(qs3)[0][0]
 
         for index, (department, elapse) in enumerate(procinst_duration_by_department):
-            if procinst_duration_by_senior >= elapse:
+            if procinst_duration_by_senior is not None and procinst_duration_by_senior >= elapse:
                 procinst_duration_by_department.insert(index, ('高管', procinst_duration_by_senior))
                 break
 

code/pep-stats-report/requirements.txt

@@ -19,11 +19,13 @@ pefile==2023.2.7
 Pillow==9.5.0
 pyinstaller==5.10.1
 pyinstaller-hooks-contrib==2023.2
+PyMuPDF==1.22.3
 pyparsing==3.0.9
 python-dateutil==2.8.2
 python-docx==0.8.11
 pytz==2023.3
 pytz-deprecation-shim==0.1.0.post0
+pywin32==306
 pywin32-ctypes==0.2.0
 qiniu==7.10.0
 requests==2.28.2