Merge pull request #16 from shartrooper/standalone-py

tweaked glossary and ph search regex

Author: shartrooper

README.md

@@ -9,4 +9,10 @@ Use both PyPDF2 and openpyxl third party modules. Descriptive header in .py file
 - Read and extract data streams from even corrupted Pdfs.
 - Directory route file search, avoid unintentional file overwriting.
 - Openpyxl data inserting and format.
-- If the column threshold is reached, the app switches into another worksheet or create a new worksheet if there's none without empty available columns, and rename Its title with the  reports date range.
+- If the column threshold is reached, the app switches into another worksheet or create a new worksheet if there's none without empty available columns, and rename Its title with the  reports date range.
+
+
+
+**TODO:**
+
+- After loading a workbook from the user input prompt (not from script exec), create a new worksheet if current report's date is well over a month of difference to prior  worksheet's dates with available column space.

getDatafromFiles.py

@@ -68,7 +68,7 @@ def __appendStringToCollection(self):
             if intoList:
                 category = "undefined category"
                 categoryRegex = re.compile(r"[\wáíúéó\s]+(?=\*)", re.IGNORECASE)
-                labelAndKeyRegex = re.compile(r"([\w\d\.\s%ñáíúéó\(\)]+)\s*:\s*([\w\d\.\s%ñáíúéó\(\)]+)", re.IGNORECASE)
+                labelAndKeyRegex = re.compile(r"([+\w\d\.\s%ñáíúéó\(\)]+)\s*:\s*([+\w\d\.\s%ñáíúéó\(\)]+)", re.IGNORECASE)
                 for i in range(0, len(intoList)):
                     categ = categoryRegex.search(intoList[i])
                     if categ:

glossary.txt

@@ -61,7 +61,7 @@ INR: inr
 TTPA: ttpa
 Dimero D: Dimero D
 GASES EN SANGRE*
-pH: gases en sangre ph
+pH: gases +en +sangre +ph
 PCO2: p co2
 PO2: p o2
 HCO3: hco3

standalone(non-beta-tweaks)/__pycache__/HGFExcelInserter.cpython-38.pyc

@@ -68,7 +68,7 @@ def __appendStringToCollection(self):
             if intoList:
                 category = "undefined category"
                 categoryRegex = re.compile(r"[\wáíúéó\s]+(?=\*)", re.IGNORECASE)
-                labelAndKeyRegex = re.compile(r"([\w\d\.\s%ñáíúéó\(\)]+)\s*:\s*([\w\d\.\s%ñáíúéó\(\)]+)", re.IGNORECASE)
+                labelAndKeyRegex = re.compile(r"([+\w\d\.\s%ñáíúéó\(\)]+)\s*:\s*([+\w\d\.\s%ñáíúéó\(\)]+)", re.IGNORECASE)
                 for i in range(0, len(intoList)):
                     categ = categoryRegex.search(intoList[i])
                     if categ:

standalone(non-beta-tweaks)/__pycache__/getDatafromFiles.cpython-38.pyc

@@ -61,7 +61,7 @@ INR: inr
 TTPA: ttpa
 Dimero D: Dimero D
 GASES EN SANGRE*
-pH: gases en sangre ph
+pH: gases +en +sangre +ph
 PCO2: p co2
 PO2: p o2
 HCO3: hco3