Create class to look for possible result sets

src/solo_turnier/html_locator.py

@@ -0,0 +1,24 @@
+import os
+import logging
+
+class HtmlLocator:
+    def __init__(self):
+        self.l = logging.getLogger('solo_turnier.html_locator')
+        self.fileName = 'erg.htm'
+    
+    def __findRecursivelyCandidates(self, path: str):
+        ret = []
+        ls = os.listdir(path)
+        
+        if self.fileName in ls and os.path.isfile(os.path.join(path, self.fileName)):
+            ret.append(os.path.join(path, self.fileName))
+        
+        for p in ls:
+            subPath = os.path.join(path, p)
+            if os.path.isdir(subPath):
+                ret = ret + self.__findRecursivelyCandidates(subPath)
+        
+        return ret
+
+    def findCandidates(self, path: str):
+        return self.__findRecursivelyCandidates(path)

src/solo_turnier/html_parser.py

@@ -1,5 +1,4 @@
 from bs4 import BeautifulSoup
-import bs4
 
 import logging
 import re
@@ -12,7 +11,7 @@ class HtmlParser:
     def parseString(self, text: str):
         soup = BeautifulSoup(text, 'html.parser')
 
-        ret = {}
+        participants = {}
 
         def __parseRows(rows, finalist: bool):
             def __parseRow(row):
@@ -32,7 +31,7 @@ class HtmlParser:
                     'place': place,
                     'finalist': finalist
                 }
-                ret[number] = participant
+                participants[number] = participant
             
             for row in rows:
                 __parseRow(row)
@@ -54,4 +53,10 @@ class HtmlParser:
 
             __parseRemainingTables(tables[1:])
 
+        title = soup.find('div', class_='eventhead').table.tr.td.contents[0]
+
+        ret = {
+            'participants': participants,
+            'title': title
+        }
         return ret

src/solo_turnier/reader.py

@@ -27,64 +27,3 @@ class AllResultReader:
         
         logging.getLogger('solo_turnier.reader.all_results').debug('Imported results from allresults.csv file: %s', ret)
         return ret
-
-class ERReader:
-    def __init__(self, fileName: str):
-        self.fileName = fileName
-        self.l = logging.getLogger('solo_turnier.reader.wert_er')
-    
-    def __parseFileContent(self, lines):
-        gruppe = re.compile('Startgruppe:\W(.+)').search(lines[2]).group(1).strip()
-        klasse = re.compile('Startklasse:\W(.+)').search(lines[3]).group(1).strip()
-        tanz = re.compile('Turnierart:\W(.+)').search(lines[4]).group(1).strip()
-
-        restLines = lines[5:]
-
-        # Search for first line with the name of the dance
-        found = -1
-        for i in range(len(restLines)):
-            if restLines[i].startswith(tanz):
-                found = i
-                break
-        
-        if found == -1:
-            self.l.warn(f'Could not find the dance {tanz} in the result file for {gruppe} ({klasse}). This might mean that the competition was not carried out.')
-            return {
-                'gruppe': gruppe,
-                'klasse': klasse,
-                'tanz': tanz,
-                'finalisten': []
-            }
-            pass
-
-        # Extract the finalists
-        finalists = []
-        for i in range(found + 1, len(restLines)):
-            if restLines[i].startswith('TopTurnier'):
-                break
-            
-            # self.l.debug('Parsing line "%s"', restLines[i].strip())
-
-            match = re.compile('[0-9]+').match(restLines[i].strip())
-            if match is None:
-                raise Exception('Could not parse starter number for end result table.')
-            else:
-                finalists.append(int(match.group(0)))
-
-        ret = {
-            'gruppe': gruppe,
-            'klasse': klasse,
-            'tanz': tanz,
-            'finalisten': finalists
-        }
-        self.l.debug('Extracted data for final: %s', ret)
-        return ret
-
-    def readFile(self):
-        with open(self.fileName, 'r') as fp:
-            lines = fp.readlines()
-        lines = [l.strip('\n') for l in lines]
-        lines = [l for  l in lines if l != '']
-        self.l.debug('Read lines for final: %s', lines)
-
-        return self.__parseFileContent(lines)

src/solo_turnier/tests/html_parser/1/expected.json

@@ -1,4 +1,5 @@
 {
+    "participants": {
         "14": {
             "name": "Max Mustermann 1",
             "place": "1.",
@@ -44,4 +45,6 @@
             "place": "9.",
             "finalist": false
         }
+    },
+    "title": "09.07.2022 - ETW, Solos Jun. Newc./Beg. Rumba"
 }

src/solo_turnier/tests/html_parser/2/expected.json

@@ -1,4 +1,6 @@
 {
+    "participants": {
+
         "14": {
             "name": "Maxime Musterfrau 1",
             "place": "1.",
@@ -24,4 +26,6 @@
             "place": "5.",
             "finalist": true
         }
+    },
+    "title": "09.07.2022 - ETW, Solos Jun. Beginner Jive"
 }

src/solo_turnier/tests/test_html_locator.py

@@ -0,0 +1,17 @@
+
+import os
+import solo_turnier.html_locator
+
+def test_fetchLocationCandidates():
+    folder = os.path.join(os.path.dirname(__file__), 'html_locator', 'export')
+    relFolder = os.path.relpath(folder)
+
+    locator = solo_turnier.html_locator.HtmlLocator()
+    candidates = locator.findCandidates(relFolder)
+
+    expected = [
+        'solo_turnier/tests/html_locator/export/2-bar/erg.htm',
+        'solo_turnier/tests/html_locator/export/3-baz/erg.htm',
+        'solo_turnier/tests/html_locator/export/3-baz/subfolder/4-baz/erg.htm'
+    ]
+    assert set(candidates) == set(expected)