Develop Reference

FPDF Python Package to Write PDF Files - Inserting extra line breaks. Does this for Multi_cell and cell. Want to remove extra line breaks

I have a python application that traverses directories on the file path passed in as a parameter. As each file is found, the file is opened and data is inserted into multi_cells.
I have checked the TXT values provided to multi_cell and there are no extra line breaks. I have played around with different setting to no avail. When inspecting the PDF output, extra line breaks are inserted. Any help would be appreciated. Look at the end of the script --- the final multicell.
import os,sys
from fpdf import FPDF
for i in range(1, len(sys.argv)):
print('argument:', i, 'value:', sys.argv[i])
mypath = sys.argv[i];
mypath = "D:\\test\\test\\CrossingTrades\\DataDictionary\\testLib\\forms"
class TOC(FPDF):
def __init__(this, orientation='P',unit='mm',format='A4'):
this._toc=[]
this._numbering=0
this._numberingFooter=0
this._numPageNum=1
FPDF.__init__(this,orientation,unit,format)
def header(self):
self.set_font('Courier', 'B', 15);
self.cell(0, 5, "Tradeflow Format and Rule Documentation", 0, 0, 'C')
self.ln(20)
def footer(self):
self.set_y(-10)
self.set_font('Arial', 'I', 8)
# Add a page number
page = 'Page ' + str(self.page_no()) + '/{nb}'
self.cell(0, 10, page, 0, 0, 'C')
def startPageNums(this):
this._numbering=1
this._numberingFooter=1
def stopPageNums(this):
this._numbering=0
def numPageNo(this):
return this._numPageNum
def TOC_Entry(this,txt,level,pageNumber):
this._numPageNum=pageNumber
this._toc+=[{'t':txt,'l':level,'p':this.numPageNo()}]
#print("PAGE NO IS ",this.numPageNo())
def insertTOC(this,location=1,labelSize=20,entrySize=10,tocfont='Times',label='Table of Contents'):
#make toc at end
this.stopPageNums()
#this.AddPage()
this.add_page();
this._numPageNum+=1
tocstart=this.page
this.set_font(tocfont,'B',labelSize)
this.cell(0,5,label,0,1,'C')
this.ln(10)
for t in this._toc:
#Offset
level=t['l']
if(level>0):
this.cell(level*8)
weight=''
if(level==0):
weight='B'
Str=t['t']
this.set_font(tocfont,weight,entrySize)
strsize=this.get_string_width(Str)
this.cell(strsize+2,this.font_size+2,Str)
#Filling dots
this.set_font(tocfont,'',entrySize)
PageCellSize=this.get_string_width(str(t['p']))+2
w=this.w-this.l_margin-this.r_margin-PageCellSize-(level*8)-(strsize+2)
#nb=w/this.get_string_width('.')
dots = "........................................................................................................"
#dots.replace('.', '.'*60, 1)
this.cell(w,this.font_size+2,dots,0,0,'R')
#Page number
this.cell(PageCellSize,this.font_size+2,str(t['p']),0,1,'R')
#grab it and move to selected location
n=this.page
n_toc = n - tocstart + 1
last = []
#store toc pages
for i in range(tocstart,n+1):
last+=[this.pages[i]]
#move pages
for i in range(tocstart-1,location-1,-1):
#~ for(i=tocstart - 1;i>=location-1;i--)
this.pages[i+n_toc]=this.pages[i]
#Put toc pages at insert point
for i in range(0,n_toc):
this.pages[location + i]=last[i]
#def Footer(this):
# if(this._numberingFooter==0):
# return
# #Go to 1.5 cm from bottom
# this.SetY(-15)
# #Select Arial italic 8
# this.SetFont('Arial','I',8)
# this.Cell(0,7,str(this.numPageNo()),0,0,'C');
# if(this._numbering==0):
# this._numberingFooter=0
class DPLFormat:
def __init__(self, name,arguments,contentsList,callerList,callingList):
self.name = name
self.arguments = arguments
self.contentsList = contentsList
self.callerList = callerList
self.callingList = callingList
class DPLRule:
def __init__(self, name,arguments,contentsList,callerList,callingList):
self.name = name
self.arguments = arguments
self.contentsList = contentsList
self.callerList = callerList
self.callingList = callingList
def get_filepaths(directory):
"""
This function will generate the file names in a directory
tree by walking the tree either top-down or bottom-up. For each
directory in the tree rooted at directory top (including top itself),
it yields a 3-tuple (dirpath, dirnames, filenames).
"""
file_paths = [] # List which will store all of the full filepaths.
#print ("Opening:", directory)
# Walk the tree.
for root, directories, files in os.walk(directory):
for filename in files:
if ".cfformat" in filename and ".cfformatprop" not in filename:
# Join the two strings in order to form the full filepath.
filepath = os.path.join(root, filename)
file_paths.append(filepath) # Add it to the list.
#file_paths.append(filename) # Add it to the list.
return file_paths # Self-explanatory.
# PDF Handling
# save FPDF() class into a
# variable pdf
pdf = TOC('P', 'mm', 'A4')
pdf.alias_nb_pages()
# Run the above function and store its results in a variable.
full_file_paths = get_filepaths(mypath)
formatList = []
tocList = []
print ("Beginning Processing ",mypath)
for index, item in enumerate(full_file_paths):
formatName = item.replace(".cfformat","")
#print(index,"",formatName)
formatArgs = ""
ruleFlag = 1
contentsList = []
callerList = []
callingList = []
#Find format in files
full_file_paths2 = get_filepaths(mypath)
cnt = 0
for index2, item2 in enumerate(full_file_paths2):
formatName2 = item2.replace(".cfformat","")
#if cnt == 0:
# print("Searching ",os.path.basename(formatName)," IN ",os.path.basename(formatName2))
with open(item2,'r') as fp2:
line2 = fp2.readline()
#print ("Opening ",os.path.basename(formatName2))
while line2:
line2 = fp2.readline()
if cnt == 0 :
if os.path.basename(formatName)in line2 and os.path.basename(formatName) != os.path.basename(formatName2) :
callerList.append(os.path.basename(formatName2))
cnt += 1
#---------------------END SEARCH FOR FORMAT IN OTHER FILES------------------
with open(item,'r') as fp:
line = fp.readline()
if "[" in line and "SQL" or ";" not in line:
formatArgs = line
ruleFlag = 0
cnt = 1
while line:
line = fp.readline()
#print("Line {}: {}".format(cnt, line.strip()))
#if "!" in line:
line = line.replace("–", "-")
#res = bytes(line,'UTF-8')
contentsList.append(line)
if "#" in line:
callingList.append(line)
cnt += 1
if formatArgs != "":
formatList.append( DPLFormat(os.path.basename(formatName),formatArgs,contentsList,callerList,callingList) )
#Now go through format files
pdf.set_font("Courier", size = 8)
formatList.sort(key=lambda x: x.name)
pdf.startPageNums()
for obj in formatList:
#print( obj.name, obj.arguments,sep =' ' )
# Add a page
pdf.add_page()
pdf.TOC_Entry(obj.name,1,pdf.page_no())
# caller list
pdf.set_font('Courier', 'B', size=13);
pdf.cell(200, 10, txt = obj.name ,
ln = 1, align = 'C')
ii = 0
pdf.set_font('Courier', 'I', size=10);
pdf.cell(200, 10, txt = "Called By: " ,
ln = 1, align = 'L')
callerStr=""
#print ("Caller list length is ", len(obj.callerList))
while ii != len (obj.callerList):
callerStr=callerStr+obj.callerList[ii]
ii += 1
pdf.multi_cell(0, 8, callerStr, 1, 'J')
#calling list
pdf.set_font('Courier', 'I', size=10);
ii = 0
pdf.cell(200, 10, txt = "Calling: " ,
ln = 1, align = 'L')
callingStr=""
#print ("Caller list length is ", len(obj.callerList))
while ii != len (obj.callingList):
callingStr=callingStr+obj.callingList[ii]
ii += 1
pdf.set_font('Courier',size=8);
pdf.multi_cell(0, 8, callingStr, 1, 'J')
#contents
pdf.set_font('Courier',size=8);
i = 0
codeStr = ""
while i != len (obj.contentsList):
codeStr=codeStr+obj.contentsList[i]
i += 1
pdf.multi_cell(0, 8, codeStr, 1, 'J')
# save the pdf with name .pdf
print ("\nWriting PDF Documentation")
pdf.insertTOC()
pdf.output("D:\\DPLAutoDoc.pdf")
print ("\nFinished")

The width in multi cell call, the first parameter is cell size or width. In portrait set that to something like 190. The second value actually controls spacing between lines so set to a value like 1 or 2. Set justification to left.

Python flask web API XML findall no attribute

import requests
try:
import xml.etree.cElementTree as et
except ImportError:
import xml.etree.ElementTree as et
user_key = "CWB-22E1B400-6B6B-4E9E-8BBF-9D78666CF958"
doc_name = "F-C0032-001"
url = "https://opendata.cwb.gov.tw/api/v1/rest/datastore/%s?Authorization=%s&format=xml" % (doc_name,user_key)
report = requests.get(url).text
#print(report)
xml_namespace = "{urn:cwb:gov:tw:cwbcommon:0.1}"
root = et.fromstring(report)
dataset = root.find(xml_namespace + 'dataset')
locations_info = dataset.findall(xml_namespace + 'location')
location = '高雄市'
target_idx = -1
for idx,ele in enumerate(locations_info):
locationName = ele[0].text
if locationName == location:
target_idx = idx
break
if target_idx != -1:
show = ''
tlist = ['天氣狀況', '最高溫', '最低溫', '舒適度', '降雨機率']
for i in range(5):
element = locations_info[target_idx][i+1]
timeblock = element[1]
data = timeblock[2][0].text
show = show + tlist[i] + ':' + data + '\n'
print(show)
else:
print('無此縣市資料')
in the Console it show
File "D:\flask\weatherdata.py", line 16, in
locations_info = dataset.findall(xml_namespace + 'location')
AttributeError: 'NoneType' object has no attribute 'findall'

I can not iterate over Python-docx document in word file

LOOK AT THE PICTUREI have the following code that reads a word docx document and write a line on the top of the table in it. It iterates over the tables inside the document. This is the old version of the code. I want to iterate over all the elements (supposely paragraphs and tables together) and insert two pointer (one for paragraphs and one for tables) and iterate with pointers. I want to write something before the previous paragraph where the data came from every table. If we have 3 tables, I want to write a sentence for every table before the last seen paragraph while we traverse the all the word file.
import docx
import section as section
from docx import Document
from docx.section import _Header
from docx.text.paragraph import Paragraph
from docx.oxml.text.paragraph import CT_P
from docx.enum.style import WD_STYLE_TYPE
import re
# Insert a empty line before the tables in the document.
def insert_paragraph_before(item, text, style=None):
"""
Return a newly created paragraph, inserted directly before this
item (Table, etc.).
"""
# CT_P.add_p_before(item._element)
p = CT_P.add_p_before(item._element)
# CT_P.add_p_before(item._element)
p2 = Paragraph(p, item._parent)
p2.text = text
p2.style = styles["REQ"]
return p2
FileName = 'Test'
document = docx.Document(FileName + ".docx")
styles = document.styles
style = styles.add_style('REQ', WD_STYLE_TYPE.PARAGRAPH)
# for table in document.tables:
# # insert_paragraph_before(table, "" )
for table in document.tables:
req_name = ""
req_id = ""
req_id_found = False
counter = 0
for row in table.rows:
for cell in row.cells:
for paragraph in cell.paragraphs:
syntax = re.compile(r'(UNIT_S-REQ|UNIT_S-DC|UNIT_S-DD|Information|MRS-REQ|MRS-DC|MRS-DD)')
result = syntax.findall(paragraph.text)
if result and req_id_found == False:
req_id = table.cell(0, 1).text
# req_id = str(result[0])
req_id_found = True
txt = table.cell(2, 1).text
# print(txt)
if txt not in ["<name>"]:
req_name = table.cell(2, 1).text
for paragraph in document.paragraphs:
if req_id_found == True:
if counter != 0:
continue
if counter == 0:
if req_id and req_name:
document.add_heading(table, "ID-" + req_id + " - " + req_name)
print(table, "ID-" + req_id + " - " + req_name)
print(paragraph.text)
elif req_id and not req_name:
document.add_heading(table, "ID-" + req_id)
print(table, "ID-" + req_id)
print(paragraph.text)
counter += 1
if counter == 0:
continue
if counter != 0:
if req_id and req_name:
document.add_paragraph(table, "ID-" + req_id + " - " + req_name)
print(table, "ID-" + req_id + " - " + req_name)
print(paragraph.text)
elif req_id and not req_name:
document.add_paragraph(table, "ID-" + req_id)
print(table, "ID-" + req_id)
print(paragraph.text)
counter += 1
document.save(FileName + "_modified.docx")

python-docx how to merge row cells

I am creating a Word document from data using python-docx. I can create all the rows and cells with no problem but, in some cases, when the current record from the database has some content in field comment, I need to add a new line to display a long content.
I tried by appending a paragraph, but the result is that the comment is appended after the table, and I need it to be added bellow the current table row.
I think the solution is to append a table row with all cells merged, but I can't find documentation to do so.
This is the code where I generate the docx file:
class OperationDOCXView(viewsets.ViewSet):
exclude_from_schema = True
def list(self, request):
from ReportsManagerApp.controllers import Operations2Controller
self.profile_id = request.query_params['profile_id']
self.operation_date = request.query_params['operation_date']
self.operation_type = request.query_params['operation_type']
self.format = request.query_params['doc_format']
operation_report_controller = Operations2Controller(self.profile_id, self.operation_date, self.operation_type)
context = operation_report_controller.get_context()
if self.format == 'json':
return Response(context)
else:
word_doc = self.get_operation_word_file(request, context)
return Response("{}{}{}".format(request.get_host(), settings.MEDIA_URL, word_doc))
def get_operation_word_file(self, request, context):
import unicodedata
from django.core.files import File
from django.urls import reverse
from docx import Document
from docx.shared import Inches, Pt
operation_type = {
'arrival': 'Llegadas',
'departure': 'Salidas',
'hotel': 'Hotel-Hotel',
'tour': 'Tours',
}
weekdays = {
'0': 'LUNES',
'1': 'MARTES',
'2': 'MIÉRCOLES',
'3': 'JUEVES',
'4': 'VIERNES',
'5': 'SÁBADO',
'6': 'DOMINGO',
}
titles = ['Booking', 'Nombre', '#', 'Vuelo', 'Hr', 'P Up', 'Traslado', 'Circuito', 'Priv?', 'Agencia', '']
widths = [Inches(1), Inches(2), Inches(0.5), Inches(1), Inches(1), Inches(1), Inches(2), Inches(3), Inches(0.5), Inches(3), Inches(0.5)]
document = Document()
section = document.sections[-1]
section.top_margin = Inches(0.5)
section.bottom_margin = Inches(0.5)
section.left_margin = Inches(0.3)
section.right_margin = Inches(0.2)
style = document.styles['Normal']
font = style.font
font.name ='Arial'
font.size = Pt(10)
company_paragraph = document.add_heading("XXXX TTOO INC")
company_paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER
description_paragraph = document.add_paragraph("Operación de {} del día {}".format(operation_type[self.operation_type], self.operation_date))
description_paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER
operation_date = self.get_operation_date().date()
operation_week_day = operation_date.weekday()
day_paragraph = document.add_paragraph(weekdays[str(operation_week_day)])
day_paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER
for provider_unit, transfers in context.items():
provider_unit_paragraph = document.add_paragraph(provider_unit)
provider_unit_paragraph.style.font.size = Pt(10)
provider_unit_paragraph.style.font.bold = False
table = document.add_table(rows=1, cols=11)
hdr_cells = table.rows[0].cells
runs = []
for i in range(len(hdr_cells)):
runs.append(self.get_hdr_cells_run(hdr_cells[i], titles[i]))
for row in table.rows:
for idx, width in enumerate(widths):
row.cells[idx].width = width
adults = 0
minors = 0
for transfer in transfers:
# table = document.add_table(rows=1, cols=11)
row_cells = table.add_row().cells
row_cells[0].text = transfer['booking']
row_cells[1].text = transfer['people']
row_cells[2].text = transfer['pax']
flight = transfer.get("flight","") if transfer.get("flight","") is not None else ""
row_cells[3].text = flight
flight_time = self.get_flight_time(flight) if flight != '' else ''
row_cells[4].text = flight_time
row_cells[5].text = transfer['pickup_time'].strftime('%H:%M') if transfer['pickup_time'] is not None else ''
row_cells[6].text = transfer['place']
row_cells[7].text = transfer['roundtrip']
row_cells[8].text = transfer['is_private']
row_cells[9].text = transfer['agency']
people = transfer['pax'].split('.')
adults = adults + int(people[0])
minors = minors + int(people[1])
if transfer['comment'] is not None:
document.add_paragraph("Comentarios: {}".format(transfer['comment']))
for row in table.rows:
for idx, width in enumerate(widths):
row.cells[idx].width = width
for cell in row.cells:
paragraphs = cell.paragraphs
for paragraph in paragraphs:
for run in paragraph.runs:
font = run.font
font.size = Pt(8)
row_cells = table.add_row().cells
row_cells[10].text = "{}.{}".format(adults, minors)
current_directory = settings.MEDIA_DIR
file_name = "Operaciones {} {}.docx".format(self.operation_type, self.operation_date)
document.save("{}{}".format(current_directory, file_name))
return file_name
def get_flight_time(self, flight):
from OperationsManagerApp.models import Flight
operation_types = {
'arrival': 'ARRIVAL',
'departure': 'DEPARTURE'
}
operation_date = datetime.strptime(self.operation_date, '%Y-%m-%d')
try:
flight = Flight.objects.get(flight_type=operation_types[self.operation_type], number=flight)
except:
return ''
else:
weekday_times = {
'0': flight.time_monday,
'1': flight.time_tuesday,
'2': flight.time_wednesday,
'3': flight.time_thursday,
'4': flight.time_friday,
'5': flight.time_saturday,
'6': flight.time_sunday,
}
weekday_time = weekday_times[str(operation_date.weekday())]
return weekday_time.strftime('%H:%M') if weekday_time is not None else ''
def get_hdr_cells_run(self, hdr_cells, title):
from docx.shared import Pt
new_run = hdr_cells.paragraphs[0].add_run(title)
new_run.bold = True
new_run.font.size = Pt(8)
return new_run
def get_operation_date(self):
date_array = self.operation_date.split('-')
day = int(date_array[2])
month = int(date_array[1])
year = int(date_array[0])
operation_date = datetime(year, month, day)
return operation_date

One approach is to add a paragraph to one of the cells:
cell.add_paragraph(transfer['comment'])
This will place it in the right position with respect to the row it belongs to, rather than after the table.
If that would take too much room for a single cell that already has another data item in it and you want to add a row, you'll need to account for that when you allocate the table. But assuming you get that worked out, merging the cells is easy:
row.cells[0].merge(row.cells[-1])

Python find function selects one match per line

I am trying to make a simple text editor using python. I am now trying to make a find function. This is what I've got:
def Find():
text = textArea.get('1.0', END+'-1c').lower()
input = simpledialog.askstring("Find", "Enter text to find...").lower()
startindex = []
endindex = []
lines = 0
if input in text:
text = textArea.get('1.0', END+'-1c').lower().splitlines()
for var in text:
character = text[lines].index(input)
start = str(lines + 1) + '.' + str(character)
startindex.append(start)
end = str(lines + 1) + '.' + str(character + int(len(input)))
endindex.append(end)
textArea.tag_add('select', startindex[lines], endindex[lines])
lines += 1
textArea.tag_config('select', background = 'green')
This will succesfully highlight words that match the users input with a green background. But the problem is, that it only highlights the first match every line, as you can see here.
I want it to highlight all matches.
Full code here: https://pastebin.com/BkuXN5pk

Recommend using the text widget's built-in search capability. Shown using python3.
from tkinter import *
root = Tk()
textArea = Text(root)
textArea.grid()
textArea.tag_config('select', background = 'green')
f = open('mouse.py', 'r')
content = f.read()
f.close()
textArea.insert(END, content)
def Find(input):
start = 1.0
length = len(input)
while 1:
pos = textArea.search(input, start, END)
if not pos:
break
end_tag = pos + '+' + str(length) + 'c'
textArea.tag_add('select', pos, end_tag)
start = pos + '+1c'
Find('display')
root.mainloop()