junte/survey-extraction
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/survey-extraction.git synced 2026-06-30 13:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use formula to get each section correctly

Browse source
This commit is contained in:
Jun-te Kim 2025-03-12 13:20:19 +00:00
parent 7aa694a5ff
commit 2fbc330c7c
1 changed files with 20 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

45
etl/pdfReader/sitenotes.py
View file

@ -238,7 +238,7 @@ class QuidosSiteNotes(SiteNotes):
def get_section_7(self): def get_section_7(self):
data = self.raw_data[self.raw_data.index('7.0 Walls'): self.raw_data.index('8.0 Roofs')] data = self.raw_data[self.raw_data.index('7.0 Walls'): self.raw_data.index('8.0 Roofs')]
avoid = [ sub_titles = [
"Construction", "Construction",
"Insulation", "Insulation",
"Insulation Thickness(mm)", "Insulation Thickness(mm)",
@ -253,24 +253,18 @@ class QuidosSiteNotes(SiteNotes):
"Alternative Wall Present", "Alternative Wall Present",
] ]
get_value = lambda key: None if self.raw_data[self.raw_data.index(key) + 1] in avoid else self.raw_data[self.raw_data.index(key) + 1] main_titles = [
"Main Property",
# Main property "Extension 1",
main_info = data[data.index("Main Property"):data.index("Extension 1")] "Extension 2",
for i,item in enumerate(main_info): "Extension 3",
if item in avoid: "Extension 4",
setattr(self, f"main_property_{item.lower().replace(' ', '_').replace('-', '_')}", get_value(item)) ]
self.two_column_with_extension_processor(data, sub_titles, main_titles, 7)
for j in range(1, 5):
main_data = data[data.index(f"Extension {j}"):]
get_value = lambda key: None if main_data[main_data.index(key) + 1] in avoid else main_data[main_data.index(key) + 1]
for i,item in enumerate(main_data):
if item in avoid:
setattr(self, f"extensions_{j}_{item.lower().replace(' ', '_').replace('-', '_')}", get_value(item))
def get_section_8(self): def get_section_8(self):
data = self.raw_data[self.raw_data.index('8.0 Roofs'): self.raw_data.index('9.0 Floors')] data = self.raw_data[self.raw_data.index('8.0 Roofs'): self.raw_data.index('9.0 Floors')]
avoid = [ sub_titles = [
"Construction", "Construction",
"Insulation Type", "Insulation Type",
"Insulation Thickness", "Insulation Thickness",
@ -285,25 +279,26 @@ class QuidosSiteNotes(SiteNotes):
"Extension 4", "Extension 4",
] ]
self.two_column_with_extension_processor(data, avoid, titles, 8) self.two_column_with_extension_processor(data, sub_titles, titles, 8)
def two_column_with_extension_processor(self, data, sub_titles, main_titles, section):
def two_column_with_extension_processor(self, data, avoid, titles, section):
title = None title = None
proc_data = data proc_data = data
for items in data: for items in data:
if items in titles: if items in main_titles:
title = items.lower().replace(" ", "_").replace("-", "_") title = items.lower().replace(" ", "_").replace("-", "_")
index = titles.index(items) index = main_titles.index(items)
if titles[index] in data: if main_titles[index] in data:
print(titles[index]) print(main_titles[index])
proc_data = data[data.index(titles[index]):] proc_data = data[data.index(main_titles[index]):]
continue continue
else: else:
break break
if title is None: if title is None:
continue continue
get_value = lambda key: None if proc_data[proc_data.index(key) + 1] in avoid else proc_data[proc_data.index(key) + 1] get_value = lambda key: None if proc_data[proc_data.index(key) + 1] in sub_titles else proc_data[proc_data.index(key) + 1]
if items in avoid: if items in sub_titles:
setattr(self, f"section_{section}_{title}_{items.lower().replace(' ', '_').replace('-','_')}", get_value(items)) setattr(self, f"section_{section}_{title}_{items.lower().replace(' ', '_').replace('-','_')}", get_value(items))
def get_section_9(self): def get_section_9(self):