def cell_with_paragraphs(self):
tc = (
a_tc().with_nsdecls()
.with_child(a_p())
.with_child(a_p())
.element
)
return _Cell(tc)
def add_table_fixture(self, request):
tc_cxml, after_tc_cxml = request.param
# the table has some overhead elements, also a blank para after since
# it's in a cell.
after_tc_cxml += (
'/(w:tblPr/w:tblW{w:type=auto,w:w=0},w:tblGrid),w:p)')
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(after_tc_cxml)
return cell, expected_xml
def add_table_fixture(self, request):
tc_cxml, after_tc_cxml = request.param
# the table has some overhead elements, also a blank para after since
# it's in a cell.
after_tc_cxml += (
'/(w:tblPr/w:tblW{w:type=auto,w:w=0},w:tblGrid),w:p)'
)
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(after_tc_cxml)
return cell, expected_xml
def __extract_table(table):
"""Extracts table data from table object"""
results = []
n = 0
for tr in table._tbl.tr_lst:
r = []
for tc in tr.tc_lst:
for grid_span_idx in range(tc.grid_span):
if tc.vMerge == ST_Merge.CONTINUE:
r.append(results[n - 1][len(r) - 1])
elif grid_span_idx > 0:
r.append(r[-1])
else:
cell = _Cell(tc, table)
r.append(cell.text.replace('\n', ' ').encode('utf8'))
results.append(r)
n += 1
return results
def __extract_table(table):
"""Extracts table data from table object"""
results = []
n = 0
for tr in table._tbl.tr_lst:
r = []
for tc in tr.tc_lst:
for grid_span_idx in range(tc.grid_span):
if tc.vMerge == ST_Merge.CONTINUE:
r.append(results[n - 1][len(r) - 1])
elif grid_span_idx > 0:
r.append(r[-1])
else:
cell = _Cell(tc, table)
r.append(cell.text.replace('\n', ' ').encode('utf8'))
results.append(r)
n += 1
return results
def cell_text_fixture(self):
# cell -------------------------
tc = (
a_tc().with_nsdecls().with_child(
a_tcPr()).with_child(
a_p()).with_child(
a_tbl()).with_child(
a_p())
).element
cell = _Cell(tc)
# text -------------------------
text = 'foobar'
# expected_xml -----------------
expected_xml = (
a_tc().with_nsdecls().with_child(
a_tcPr()).with_child(
a_p().with_child(
an_r().with_child(
a_t().with_text(text))))
).xml()
return cell, text, expected_xml
def table_print(b):
try:
for row in b.rows:
for cell in row.cells:
for paragraph in cell.paragraphs:
if (not len(paragraph.text) == 0):
translator = Translator()
tran = translator.translate(paragraph.text, dest='hi')
paragraph.text = tran.text
except Exception as e:
for tc in b._tbl.iter_tcs():
cell = _Cell(tc, b)
for b_tc in iter_block_items(cell):
if isinstance(b_tc, Paragraph):
if (not len(b_tc.text) == 0):
try:
translator = Translator()
tran = translator.translate(b_tc.text, dest='hi')
b_tc.text = tran.text
print("_______Trasnlating______\n")
except:
pass
def tables_fixture(self, request):
cell_cxml, expected_count = request.param
cell = _Cell(element(cell_cxml), None)
return cell, expected_count
def width_get_fixture(self, request):
tc_cxml, expected_width = request.param
cell = _Cell(element(tc_cxml), None)
return cell, expected_width
def merge_fixture(self, tc_, tc_2_, parent_, merged_tc_):
cell, other_cell = _Cell(tc_, parent_), _Cell(tc_2_, parent_)
tc_.merge.return_value = merged_tc_
return cell, other_cell, merged_tc_
def paragraphs_fixture(self):
return _Cell(element('w:tc/(w:p, w:p)'), None)
def add_paragraph_fixture(self, request):
tc_cxml, after_tc_cxml = request.param
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(after_tc_cxml)
return cell, expected_xml
def alignment_set_fixture(self, request):
cxml, new_value, expected_cxml = request.param
cell = _Cell(element(cxml), None)
expected_xml = xml(expected_cxml)
return cell, new_value, expected_xml
def width_set_fixture(self, request):
tc_cxml, new_value, expected_cxml = request.param
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(expected_cxml)
return cell, new_value, expected_xml
def add_paragraph_fixture(self, request):
tc_cxml, after_tc_cxml = request.param
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(after_tc_cxml)
return cell, expected_xml
def add_table_fixture(self, request):
cell = _Cell(element('w:tc/w:p'), None)
expected_xml = snippet_seq('new-tbl')[1]
return cell, expected_xml
def alignment_get_fixture(self, request):
tc_cxml, expected_value = request.param
cell = _Cell(element(tc_cxml), None)
return cell, expected_value
def paragraphs_fixture(self):
return _Cell(element('w:tc/(w:p, w:p)'), None)
def merge_fixture(self, tc_, tc_2_, parent_, merged_tc_):
cell, other_cell = _Cell(tc_, parent_), _Cell(tc_2_, parent_)
tc_.merge.return_value = merged_tc_
return cell, other_cell, merged_tc_
def alignment_get_fixture(self, request):
tc_cxml, expected_value = request.param
cell = _Cell(element(tc_cxml), None)
return cell, expected_value
def width_set_fixture(self, request):
tc_cxml, new_value, expected_cxml = request.param
cell = _Cell(element(tc_cxml), None)
expected_xml = xml(expected_cxml)
return cell, new_value, expected_xml
def add_table_fixture(self, request):
cell = _Cell(element('w:tc/w:p'), None)
expected_xml = snippet_seq('new-tbl')[1]
return cell, expected_xml
def tables_fixture(self, request):
cell_cxml, expected_count = request.param
cell = _Cell(element(cell_cxml), None)
return cell, expected_count
def alignment_set_fixture(self, request):
cxml, new_value, expected_cxml = request.param
cell = _Cell(element(cxml), None)
expected_xml = xml(expected_cxml)
return cell, new_value, expected_xml
def width_get_fixture(self, request):
tc_cxml, expected_width = request.param
cell = _Cell(element(tc_cxml), None)
return cell, expected_width
def pre_story(input_file, un_match_tokens=None):
# print(un_match_tokens)
un_match_tokens = un_match_tokens.split('$zl$')
try:
import os
result_file = input_file[:input_file.rfind('.')] + '_new' + input_file[
input_file.rfind('.'):]
word_obj = docx.Document(input_file)
for cur_table_index in range(len(word_obj.tables)):
cur_table = word_obj.tables[cur_table_index]
for cur_row_index_cur_table in range(len(cur_table.rows)):
for cur_col_index_cur_row in range(len(cur_table.columns)):
# # 得到当前单元格
cur_cell = cur_table.cell(cur_row_index_cur_table,
cur_col_index_cur_row)
cur_tc_list = cur_cell._tc
cur_cell_text_list = []
for cur_tc_index in range(len(cur_tc_list) - 1, -1, -1):
# 初始化变量
cur_tc = cur_tc_list[cur_tc_index]
delete_and_add_element = -1
delete_and_add_element += 1
cur_tc_text = ''
if isinstance(cur_tc, CT_P):
# # 如果是文本段落的话, 判断段落是否空，空的话跳过，不空的话，删掉重新加
# print(cur_tc, cur_tc.r_lst)
for cur_r_in_cur_tc_r_list in cur_tc.r_lst:
cur_tc_text += cur_r_in_cur_tc_r_list.text
# print(cur_tc, cur_tc_text, bool(cur_tc_text and not cur_tc_text.isspace()))
if bool(cur_tc_text and not cur_tc_text.isspace()):
# 删掉这个，并增加一个段落。
delete_and_add_element = 1
cur_cell_text_list.insert(0, cur_tc_text)
else:
delete_and_add_element = 0
elif isinstance(cur_tc, CT_Tbl):
delete_and_add_element = 0
child_table_cur_tc = cur_tc
for child_table_row in child_table_cur_tc.tr_lst:
for child_table_cell in child_table_row.tc_lst:
# 嵌套表的当前单元格 child_table_cell
block_list_child_table_cell = list(
child_table_cell.iter_block_items())
cur_cell_child_table_text_list = []
for cur_block_child_table_cell_index in range(
len(block_list_child_table_cell) -
1, -1, -1):
# 初始化嵌套表里的变量。
cur_block_child_table_cell = \
block_list_child_table_cell[cur_block_child_table_cell_index]
delete_and_add_element_child_table = -1
delete_and_add_element_child_table += 1
cur_tc_text_child_table = ''
if isinstance(
cur_block_child_table_cell,
CT_P):
# # 如果是文本段落的话, 判断段落是否空，空的话跳过，不空的话，删掉重新加
for cur_r_in_cur_tc_r_list in cur_block_child_table_cell.r_lst:
cur_tc_text_child_table += cur_r_in_cur_tc_r_list.text
# import pdb
# pdb.set_trace()
# print(cur_tc_text_child_table, bool(cur_tc_text_child_table and not cur_tc_text_child_table.isspace()))
if bool(cur_tc_text_child_table and
not cur_tc_text_child_table
.isspace()):
# 删掉这个，并增加一个段落。
delete_and_add_element_child_table = 1
cur_cell_child_table_text_list.insert(
0, cur_tc_text_child_table)
else:
delete_and_add_element_child_table = 0
else:
# # 如果不是CT_P，就跳过
delete_and_add_element_child_table = 0
if delete_and_add_element_child_table == 1:
for p_zl in block_list_child_table_cell[
cur_block_child_table_cell_index].r_lst:
p_zl.text = ''
del block_list_child_table_cell[
cur_block_child_table_cell_index]
# # 在嵌套表中增加段落，改颜色
for cur_add_text_index, cur_add_text in enumerate(
cur_cell_child_table_text_list):
cell_buffer = _Cell(
child_table_cell,
child_table_cur_tc)
run = cell_buffer.paragraphs[
-1].add_run(cur_add_text)
# if cur_add_text_index == 0:
# run = cell_buffer.paragraphs[-1].add_run(cur_add_text)
# else:
# run = cell_buffer.paragraphs[-1].add_run(cur_add_text)
run.font.name = '宋体'
run.font.size = 140000
# run.font.color.rgb = RGBColor(255, 0, 0)
if not cur_add_text.isspace():
run.font.highlight_color = 4
if un_match_tokens is not None and cur_add_text in un_match_tokens:
run.font.highlight_color = 7
un_match_tokens.remove(
cur_add_text)
else:
# # 其他情况
delete_and_add_element = 0
if delete_and_add_element == 1:
del cur_tc_list[cur_tc_index]
for cur_add_text_index, cur_add_text in enumerate(
cur_cell_text_list):
if cur_add_text_index == 0:
run = cur_cell.add_paragraph().add_run(
cur_add_text)
else:
run = cur_cell.paragraphs[-1].add_run(cur_add_text)
run.font.name = '宋体'
run.font.size = 140001
# run.font.color.rgb = RGBColor(255, 0, 0)
if not cur_add_text.isspace():
run.font.highlight_color = 4
if un_match_tokens is not None and cur_add_text in un_match_tokens:
run.font.highlight_color = 7
un_match_tokens.remove(cur_add_text)
for i in range(len(word_obj.paragraphs)):
cur_p = word_obj.paragraphs[i]
cur_p_text = cur_p.text
cur_p.text = ''
run = cur_p.add_run(cur_p_text)
if not cur_p_text.isspace():
run.font.highlight_color = 4
#print('zlzlzl', cur_p_text, un_match_tokens)
if un_match_tokens is not None and cur_p_text in un_match_tokens:
run.font.highlight_color = 7
un_match_tokens.remove(cur_p_text)
word_obj.save(result_file)
except Exception as e:
result_file = input_file
return result_file
