def test_extract_with_span(self):
""" Extract a text with a bold/italic span """
poem_odt = os.path.join(
os.path.dirname(__file__), u"examples", u"simplestyles.odt")
d = load(poem_odt)
teletype.extractText(d.body)
self.assertEqual(u'Plain textBoldItalicBold italicUnderlineUnderline italicUnderline bold italicKm2 - superscriptH2O - subscript', teletype.extractText(d.body))
def test_extract_with_span(self):
""" Extract a text with a bold/italic span """
poem_odt = os.path.join(
os.path.dirname(__file__), "examples", "simplestyles.odt")
d = load(poem_odt)
teletype.extractText(d.text)
self.assertEqual(u'Plain textBoldItalicBold italicUnderlineUnderline italicUnderline bold italicKm2 - superscriptH2O - subscript', teletype.extractText(d.text))
def _get_conclusion_from_report(report):
conclusion = []
try:
doc = load(report.path)
except FileNotFoundError:
return 'Не найдено'
paragraphs = doc.getElementsByType(text.P)
for i in range(len(paragraphs)):
if teletype.extractText(
paragraphs[i]).strip().startswith('Заключение:'):
conclusion.append(
teletype.extractText(paragraphs[i]).replace(
'Заключение:', '').strip())
return '; '.join(conclusion)
def convert_text_only(self):
"""Конвертация текста в файле ODT.
Конвертируется все содерржимое <body>.
Результат записывается в файл *.cnv.odt
:return: None
"""
body = self.doc.body
new_doc = OpenDocumentText()
for _body_elem in body.childNodes:
for _elem in _body_elem.childNodes:
body_text = teletype.extractText(_elem)
body_text = self.converter(body_text)
para = text.P()
teletype.addTextToElement(para, body_text)
new_doc.text.addElement(para)
# print(body_text)
# Замена шрифта в стилях.
if self.style_font:
self.set_font_for_all_styles()
_suffix = '.all.odt'
if self.extension:
_suffix = self.extension
new_odt = self.p_odt.with_suffix(_suffix)
new_doc.save(new_odt.as_posix())
def load_file(self, file):
textdoc = load(file)
allparas = textdoc.getElementsByType(text.P)
allparas = [teletype.extractText(_) for _ in allparas]
allparas = [_ for _ in allparas if len(_) > 20]
self.allparas = allparas
self.is_valid = True
def getODTContent(filename):
list = []
textdoc = load(filename)
allparas = textdoc.getElementsByType(text.P)
for i in range(len(allparas)):
list.append(teletype.extractText(allparas[i]))
return ' '.join(list)
def cargar_desde_carpeta(dataset):
txt_declaracion = []
n = 0
for item in dataset:
n = n + 1
print(n)
id_file = extraer_id(item)
if id_file:
try:
destination = 'doc/myfile_' + id_file + '.odt'
textdoc = load(destination)
allparas = textdoc.getElementsByType(text.P)
texto = []
for i in allparas:
texto.append(teletype.extractText(i))
texto = ' '.join(texto)
except:
try:
from tika import parser
destination = 'doc/myfile_' + id_file + '.pdf'
file_data = parser.from_file(destination)
texto = file_data['content']
except:
texto = "Archivo no encontrado"
txt_declaracion.append(texto)
else:
txt_declaracion.append('NADA')
return txt_declaracion
def __replace_text_in_odf_element(a_file, a_element_foo, a_replace_map: list):
replace_map = {}
for element in a_file.getElementsByType(a_element_foo):
text = teletype.extractText(element)
for mark in a_replace_map:
text = text.replace(mark[0], mark[1])
new_odf_element = odf_text.P()
new_odf_element.setAttribute("stylename",
element.getAttribute("stylename"))
for space_elements in element.getElementsByType(odf_text.S):
# Без этого все пробельные символы в начале строк удалятся
spaces = space_elements.getAttribute('c')
if spaces is not None:
new_space_element = odf_text.S()
new_space_element.setAttribute('c', spaces)
new_odf_element.appendChild(new_space_element)
new_odf_element.addText(text)
replace_map[element] = new_odf_element
for old, new in replace_map.items():
old.parentNode.insertBefore(new, old)
old.parentNode.removeChild(old)
# Без этого дерево нодов сломается
a_file.rebuild_caches(new.parentNode)
def openFile():
filename = tk.filedialog.askopenfilename(initialdir ='C:\\')
if len(filename)==0:
print("open file for reading is cancelled.")
return
filetype=filename.split(".")
filetype=filetype[len(filetype)-1]
if(filetype=="txt"):
try:
file=open(filename,'r')
t=create_newtext()
t.insert('end',file.read())
file.close()
except IOError as e:
print(e,filename)
elif(filetype=="odt"):
textdoc = load(filename)
allparas = textdoc.getElementsByType(text.P)
t=create_newtext()
for i in range(len(allparas)):
t.insert('end',teletype.extractText(allparas[i]))
else:
tk.messagebox.showinfo( title='Unsupported file type',
message='This is unsupported file type, now the supported file type are .txt and .odt')
def getODTText(self, file): #odt datei wird gelesen
fileName = file
textdoc = load(fileName)
allparas = textdoc.getElementsByType(text.P)
outputlist = []
for x in allparas:
outputlist.append(teletype.extractText(x))
self.FinalOutputText = "".join(outputlist)
def odt_analysis(file, pattern, path):
"""Finds the pattern in text (and images) for .odt files"""
counter = 0
textdoc = load(file)
all_paragraphs = textdoc.getElementsByType(otext.P)
for paragraph in all_paragraphs:
counter += teletype.extractText(paragraph).lower().count(pattern)
show(path, file, counter)
def __read_text_cell(self, cell):
text_content = []
paragraphs = cell.getElementsByType(P)
# for each text node
for paragraph in paragraphs:
data = extractText(paragraph)
text_content.append(data)
return '\n'.join(text_content)
def parse_odt(response):
tmp = tempfile.NamedTemporaryFile()
with open(tmp.name, "wb") as f:
f.write(response.content)
odtfile = opendocument.load(tmp.name)
texts = odtfile.getElementsByType(text.P)
return " ".join(teletype.extractText(t) for t in texts)
def get_text(self):
out_text = ''
body = self.doc.body
for _body_elem in body.childNodes:
for _elem in _body_elem.childNodes:
body_text = teletype.extractText(_elem)
out_text += f'{body_text}\n'
return out_text
def 讀odt檔(檔名):
if '.odt' not in 檔名:
exit(0)
textdoc = load(檔名)
內容陣列 = []
for line in textdoc.getElementsByType(text.P):
tsua = teletype.extractText(line).strip()
內容陣列.append(tsua)
return 內容陣列
def __read_text_cell(self, cell):
text_content = []
paragraphs = cell.getElementsByType(P)
# for each text node
for paragraph in paragraphs:
name_space, tag = paragraph.parentNode.qname
if tag != str("annotation"):
data = extractText(paragraph)
text_content.append(data)
return "\n".join(text_content)
def extraer_texto_odt(file_id):
destination = 'doc/myfile_' + file_id + '.odt'
download_from_drive(file_id, destination)
textdoc = load(destination)
allparas = textdoc.getElementsByType(text.P)
texto = []
for i in allparas:
texto.append(teletype.extractText(i))
texto = ' '.join(texto)
return texto
def noteline_identification(self, ligne):
text = teletype.extractText(ligne)
for i in range(len(text)):
if (self.check_char_note(text[i])):
if (text[i + 1] == " " or text[i + 1] == "#"
or (text[i + 1] == "b" and
(text[i + 2] == " " or text[i + 2].lower == "m"
or text[i + 2] == "/"))):
return True
return False
def __read_text_cell(self, cell):
text_content = []
paragraphs = cell.getElementsByType(P)
# for each text node
for paragraph in paragraphs:
name_space, tag = paragraph.parentNode.qname
if tag != str("annotation"):
data = extractText(paragraph)
text_content.append(data)
return "\n".join(text_content)
def odf_to_text(document_path, event_handler):
from odf.opendocument import load as odf_load
from odf import text as odf_text
from odf import teletype as odf_teletype
doc = odf_load(document_path)
paragraphs = []
for p in doc.getElementsByType(odf_text.P):
paragraphs.append(odf_teletype.extractText(p))
return '\n'.join(paragraphs).strip()
def test_extract(self):
""" Convert a paragraph to plain text """
poem_odt = os.path.join(os.path.dirname(__file__), u"examples",
u"serious_poem.odt")
d = load(poem_odt)
allparas = d.getElementsByType(P)
content = u"""<text:p text:style-name="Standard">The boy stood <text:s text:c="3"/>on the burning deck,<text:line-break/><text:tab/>Whence all<text:tab/>but<text:tab/><text:tab/>him had fled.<text:line-break/>The flames <text:s text:c="2"/>that lit<text:tab/>the battle's<text:tab/>wreck,<text:line-break/> <text:s text:c="11"/>Shone o'er him, round the dead. <text:s text:c="2"/></text:p>"""
self.assertEqual(
u"The boy stood on the burning deck,\n\tWhence all\tbut\t\thim had fled.\nThe flames that lit\tthe battle's\twreck,\n Shone o'er him, round the dead. ",
teletype.extractText(allparas[0]))
def odftext(self):
"""Extract texts from .odt/.ods/.odp files"""
odf_file = odfload(self.path)
odf_text = odf_file.getElementsByType(odftext.P)
text = ''
for para in odf_text:
t = teletype.extractText(para)
text = text + t + ' '
text = text.replace("'", "‘")
return text
def test_extract(self):
""" Convert a paragraph to plain text """
poem_odt = os.path.join(os.path.dirname(__file__), "examples", "serious_poem.odt")
d = load(poem_odt)
allparas = d.getElementsByType(P)
content = """<text:p text:style-name="Standard">The boy stood <text:s text:c="3"/>on the burning deck,<text:line-break/><text:tab/>Whence all<text:tab/>but<text:tab/><text:tab/>him had fled.<text:line-break/>The flames <text:s text:c="2"/>that lit<text:tab/>the battle's<text:tab/>wreck,<text:line-break/> <text:s text:c="11"/>Shone o'er him, round the dead. <text:s text:c="2"/></text:p>"""
self.assertEqual(
u"The boy stood on the burning deck,\n\tWhence all\tbut\t\thim had fled.\nThe flames that lit\tthe battle's\twreck,\n Shone o'er him, round the dead. ",
teletype.extractText(allparas[0]),
)
def switch_notes(self, qte):
for i in range(len(self.lignes)):
#print(self.allText[self.lignes[i]])
#ligne de notes
old_text = teletype.extractText(self.allText[self.lignes[i]])
newer_text = ""
new_notes = []
for j in range(len(self.notes[i].notes)):
new_notes.append(
self.gamme.switch_note(self.notes[i].notes[j], self.bemol,
qte).note)
print("NOTESET")
self.notes[i].show_noteset()
print("NEW NOTESET : " + str(new_notes))
cpt = 0
for j in range(len(old_text) - 1):
if old_text[j] != " " and old_text[j] != "/" and (
old_text[j] == self.notes[i].notes[cpt].note or
(old_text[j] + old_text[j + 1])
== self.notes[i].notes[cpt].note):
print("NEW NOTE")
newer_text += new_notes[cpt]
cpt += 1
if (cpt == len(new_notes)):
newer_text += " "
break
else:
if (old_text[j] != "b" and old_text[j] != "#"):
newer_text += old_text[j]
print("OLD TEXT : " + old_text)
print("NEW TEXT : " + newer_text)
new_S = text.P()
new_S.setAttribute(
"stylename",
self.allText[self.lignes[i]].getAttribute("stylename"))
new_S.addText(newer_text)
self.allText[self.lignes[i]] = new_S
# print("\n\n\n")
# for i in range(len(self.allText)):
# print(self.allText[i])
self.reset_notes()
def __init__(self, ligne):
self.notes = []
self.gamme = Gamme()
text = teletype.extractText(ligne)
for i in range(len(text)):
if text[i] in self.gamme.notes:
new_note = text[i]
if text[i + 1] == "b":
new_note += "b"
elif text[i + 1] == "#":
new_note += "#"
self.notes.append(Note(new_note))
def get_text_odt(file_path):
""" Function to extract the text from an ODT file
Args:
file_path (str): local path to file
Returns:
String with all the text from the ODT file
"""
textdoc = load(file_path)
full_text = []
for para in textdoc.getElementsByType(odf_text.P):
full_text.append(teletype.extractText(para))
return ' '.join(full_text)
def read_files(p):
filename, file_extension = os.path.splitext(p)
if (file_extension in [".txt", ".py", ".cpp", ".c"]):
with open(p, 'r') as file:
data = file.read()
return data
elif (file_extension == ".pdf"
): ## TODO: needs tuning sometimes does not work
#print("handling pdf:")
data = []
t = ""
with open(p, 'rb') as file:
pdfReader = PyPDF2.PdfFileReader(file)
for i in range(pdfReader.numPages):
pageObj = pdfReader.getPage(i)
data.append(pageObj.extractText())
t = '\n'.join(data)
return (t)
## TODO: TEXTRACT STILL NOT FIXED
'''
if (not len(text)):
print("HERE")
text = textract.process(p, method='tesseract', language='eng')
'''
'''
### Testing slate3k
with open(p, 'rb') as file:
extracted_text = slate.PDF(file)
return(extracted_text)
'''
elif (file_extension == ".docx"):
#print("handling docx:")
doc = docx.Document(p)
data = []
for para in doc.paragraphs:
data.append(para.text)
return '\n'.join(data)
elif (file_extension == ".odt"):
#print("handling odt:")
textdoc = load(p)
data = []
allparas = textdoc.getElementsByType(text.P)
for i in range(len(allparas)):
data.append(teletype.extractText(allparas[i]))
return '\n'.join(data)
def __fill_odf_table(a_file, a_tables_to_draw: List[TableToDraw]):
for table in a_file.getElementsByType(odf_table.Table):
for table_row in table.getElementsByType(odf_table.TableRow):
if teletype.extractText(table_row) == "%insert_table__":
cell_style = table_row.getElementsByType(
odf_table.TableCell)[0].getAttribute("stylename")
text_style = table_row.getElementsByType(
odf_text.P)[0].getAttribute("stylename")
row_length_in_cells = __get_table_columns_count(table)
# Удаляем флаговую строку
table_row.parentNode.removeChild(table_row)
for table_to_draw in a_tables_to_draw:
table_header = [
"Тип сигнала: " + table_to_draw.signal_type,
"Предел измерения: " + table_to_draw.limit,
"Допустимая погрешность: " + table_to_draw.error_limit
]
__add_row_with_texts_to_table(table, None, cell_style,
table_header,
row_length_in_cells)
for frequency in table_to_draw.points.keys():
if int(frequency) != 0:
__add_row_with_text_to_table(
table, None, cell_style,
' '.join(["Частота:",
str(frequency),
"Гц"]), row_length_in_cells)
for points in table_to_draw.points[frequency]:
points_row = __add_row_to_table(table)
for point in points:
__add_cell_to_row(points_row, cell_style,
text_style, str(point))
for empty_cell in range(row_length_in_cells -
len(points)):
# Чтобы пустые ячейки не мерджились в одну
__add_cell_to_row(points_row, cell_style,
text_style, "")
# Без этого дерево нодов сломается
a_file.rebuild_caches(table_row.parentNode)
break
def switch_type(self):
for i in range(len(self.lignes)):
old_text = teletype.extractText(self.allText[self.lignes[i]])
new_text = ""
new_notes = []
cpt = 0
for j in range(len(self.notes[i].notes)):
ind = self.get_char_index(self.notes[i].notes[j].note)
if self.bemol:
new_notes.append(self.gamme.notes_diese[ind])
else:
new_notes.append(self.gamme.notes_bemol[ind])
print("NOTES : " + str(new_notes))
for j in range(len(old_text) - 1):
if old_text[j] != " " and old_text[j] != "/" and (
old_text[j] == self.notes[i].notes[cpt].note or
(old_text[j] + old_text[j + 1])
== self.notes[i].notes[cpt].note):
print("NEW NOTE")
new_text += new_notes[cpt]
cpt += 1
if (cpt == len(new_notes)):
new_text += " "
break
else:
if (old_text[j] != "b" and old_text[j] != "#"):
new_text += old_text[j]
print("OLD TEXT : " + old_text)
print("NEW TEXT : " + new_text)
new_S = text.P()
new_S.setAttribute(
"stylename",
self.allText[self.lignes[i]].getAttribute("stylename"))
new_S.addText(new_text)
self.allText[self.lignes[i]] = new_S
self.bemol = not self.bemol
self.reset_notes()
def get_text_from_odt(_odt, save_blank=None) -> str:
"""Выводит текст odt документа.
Абзацы (\n), табуляции(\t), переносы строк (\n) обрабатываются.
:param _odt:
:param save_blank: Сохранять ли промежутки между абзацами как \n
:return: text
"""
# TODO: save_blank - как в pandoc.
doc = load(_odt)
out_text = ''
body = doc.body
for _body_elem in body.childNodes:
for _elem in _body_elem.childNodes:
body_text = teletype.extractText(_elem)
out_text += f'{body_text}\n'
return out_text
def con(filenames, code, counter, subdir):
if not os.path.exists('input/' + subdir):
os.makedirs('input/' + subdir)
for file in filenames:
counter = counter + 1
txtString = []
textfile = load(file)
allparas = textfile.getElementsByType(text.P)
for texts in allparas:
txtString.append(teletype.extractText(texts))
saveFile = open("input/" + subdir + '/' + str(code) +
str(counter).zfill(4) + ".txt",
'w',
encoding="utf-8")
saveFile.write(''.join(txtString))
saveFile.close()
return counter
def clean_file(file_path):
doc = load(file_path)
texts = doc.getElementsByType(text.P)
s = len(texts)
started = False
line_items = []
for i in range(s):
line = teletype.extractText(texts[i])
if 'END OF MINIDISCS' in line:
break
if not started and 'DISC 1' in line:
started = True
if started and line and not any(a_word in line
for a_word in skip_words):
line_items.append(line)
return line_items
def __init__(self, ligne):
self.notes = []
self.gamme = Gamme()
text = teletype.extractText(ligne)
for i, txt in enumerate(text):
if txt in self.gamme.notes:
new_note = txt
if text[i + 1] == "b":
new_note += "b"
elif text[i + 1] == "#":
new_note += "#"
self.notes.append(Note(new_note))
def main():
global grid
global month_year
if len(sys.argv)==1: cmd_line="ncal -h"
else: cmd_line="ncal -h -m %s" %(sys.argv[1])
cal_prc=subprocess.Popen(cmd_line.split(' '),stdout=subprocess.PIPE)
cal_str_lst_tr=cal_prc.communicate()[0].split('\n')
cal_str_lst=[cal_str_lst_tr[0]]
for c in xrange(7):
line=u""
for l in xrange(7):
st=(cal_str_lst_tr[l+1].decode("utf-8")+u" ")[c*3:(c*3+3)]
line=line+st
cal_str_lst.append(line)
month_year=cal_str_lst[0].strip()
header=cal_str_lst[1].split(' ')
header=[i for i in header if len(i)>0]
for n in cal_str_lst:
ned=[]
if (len(n)>20):
for d in xrange(7):
day=''+n[3*d]+n[(3*d)+1]
ned.append(day)
grid.append(ned)
grid=grid[2:]
cal=load("template_ru.ods")
texts = cal.getElementsByType(text.P)
s=len(texts)
for i in range(s):
old_text = teletype.extractText(texts[i]).encode("utf-8")
new_text =replace_tmpl(old_text)
if new_text!=None:
new_S = text.P()
new_S.setAttribute("stylename",texts[i].getAttribute("stylename"))
new_S.addText(new_text)
texts[i].parentNode.insertBefore(new_S,texts[i])
texts[i].parentNode.removeChild(texts[i])
cal.save("календарь на %s.ods" %(month_year))
def read_file(self):
odtfile = load(self.path)
texts = odtfile.getElementsByType(text.P)
self.content = " ".join(teletype.extractText(t) for t in texts)