lines: support "rules" field for multiple sets of parsing regexes

TUTORIAL.md

@@ -137,6 +137,10 @@ This parser allows parsing selected invoice section as a set of lines
 sharing some pattern. Those can be e.g. invoice items (good or services)
 or VAT rates.
 
+Some companies may use multiple formats for their line-based data. In
+such cases multiple sets of parsing regexes can be added to the `rules`.
+Results from multiple `rules` get merged into a single array.
+
 It replaces `lines` plugin and should be preferred over it. It allows
 reusing in multiple `fields`.
 
@@ -149,6 +153,17 @@ Example for `fields`:
         end: \s+Total
         line: (?P<description>.+)\s+(?P<discount>\d+.\d+)\s+(?P<price>\d+\d+)
 
+    fields:
+      lines:
+        parser: lines
+        rules:
+          - start: Item\s+Discount\s+Price$
+            end: \s+Total
+            line: (?P<description>.+)\s+(?P<discount>\d+.\d+)\s+(?P<price>\d+\d+)
+          - start: Item\s+Price$
+            end: \s+Total
+            line: (?P<description>.+)\s+(?P<price>\d+\d+)
+
 ### Legacy regexes
 
 For non-text fields, the name of the field is important:

src/invoice2data/extract/parsers/lines.py

@@ -115,10 +115,10 @@ def parse_block(template, field, settings, content):
     return lines
 
 
-def parse(template, field, _settings, content):
+def parse_by_rule(template, field, rule, content):
     # First apply default options.
     settings = DEFAULT_OPTIONS.copy()
-    settings.update(_settings)
+    settings.update(rule)
 
     # Validate settings
     assert "start" in settings, "Lines start regex missing"
@@ -152,6 +152,24 @@ def parse(template, field, _settings, content):
     return lines
 
 
+def parse(template, field, settings, content):
+    if "rules" in settings:
+        # One field can have multiple sets of line-parsing rules
+        rules = settings['rules']
+    else:
+        # Original syntax stored line-parsing rules in top field YAML object
+        keys = ('start', 'end', 'line', 'first_line', 'last_line', 'skip_line', 'types')
+        rules = [{k: v for k, v in settings.items() if k in keys}]
+
+    lines = []
+    for rule in rules:
+        new_lines = parse_by_rule(template, field, rule, content)
+        if new_lines is not None:
+            lines += new_lines
+
+    return lines
+
+
 def parse_current_row(match, current_row):
     # Parse the current row data
     for field, value in match.groupdict().items():

tests/custom/lines-multiple-patterns.json

@@ -17,6 +17,13 @@
             { "pos": 6, "name": "Penguin" },
             { "pos": 7, "name": "Ostrich" }
         ],
+        "dimensions": [
+            { "pos": 1, "angle": 30, "length": 30 },
+            { "pos": 2, "angle": 45, "length": 40 },
+            { "pos": 3, "angle": 90, "length": 60 },
+            { "pos": 4, "length": 80, "angle": 135 },
+            { "pos": 5, "length": 100, "angle": 180 }
+        ],
         "currency": "EUR",
         "desc": "Invoice from Lines Tests"
     }

tests/custom/lines-multiple-patterns.txt

@@ -5,6 +5,7 @@ Total: 50.00 EUR
 
 Lines with multiple patterns
 
+
 Lines start
 
 Group: Mammals
@@ -21,3 +22,15 @@ Subgroup: Flightless
 7. Ostrich
 
 Lines end
+
+
+No  Angle [°]  Length [cm]
+1   30         30
+2   45         40
+3   90         60
+Count: 3
+
+No  Length [cm]  Angle [°]
+4   80           135
+5   100          180
+Count: 2

tests/custom/templates/lines-multiple-patterns.yml

@@ -26,6 +26,23 @@ fields:
       - ^Subgroup:\s*(?P<subgroup>.+)$
     types:
       pos: int
+  dimensions:
+    parser: lines
+    rules:
+      - start: No.*Angle.*Length
+        end: Count
+        line: ^(?P<pos>\d+)\s+(?P<angle>\d+)\s+(?P<length>\d+)$
+        types:
+          pos: int
+          angle: int
+          length: int
+      - start: No.*Length.*Angle
+        end: Count
+        line: ^(?P<pos>\d+)\s+(?P<length>\d+)\s+(?P<angle>\d+)$
+        types:
+          pos: int
+          angle: int
+          length: int
 options:
   currency: EUR
   date_formats: