fix: replace AnnType with LayerEnum

openpecha/core/layer.py

@@ -4,9 +4,9 @@
 
 from pydantic import BaseModel, validator
 
-from .annotations import *
-from .ids import get_uuid
-from .metadata import PechaMetadata
+from openpecha.core.annotations import *
+from openpecha.core.ids import get_uuid
+from openpecha.core.metadata import PechaMetadata
 
 
 class LayerEnum(Enum):
@@ -28,6 +28,7 @@ class LayerEnum(Enum):
     correction = "Correction"
     error_candidate = "ErrorCandidate"
     peydurma = "Peydurma"
+    pedurma_note = "PedurmaNote"
     sabche = "Sabche"
     tsawa = "Tsawa"
     yigchung = "Yigchung"
@@ -87,6 +88,7 @@ def _get_annotation_class(layer_name: LayerEnum):
     else:
         return BaseAnnotation
 
+
 class Layer(BaseModel):
     id: str = None
     annotation_type: LayerEnum
@@ -125,7 +127,7 @@ def get_annotation(self, annotation_id: str) -> Optional[BaseAnnotation]:
         ann = ann_class.parse_obj(ann_dict)
         return ann
 
-    def set_annotation(self, ann: BaseAnnotation, ann_id = None):
+    def set_annotation(self, ann: BaseAnnotation, ann_id=None):
         """Add or Update annotation `ann` to the layer, returns the annotation id"""
         ann_id = ann_id if ann_id is not None else get_uuid()
         self.annotations[ann_id] = json.loads(ann.json())
@@ -145,4 +147,4 @@ class SpanINFO(BaseModel):
 
 class OCRConfidenceLayer(Layer):
     confidence_threshold: float
-    annotation_type: LayerEnum = LayerEnum.ocr_confidence
+    annotation_type: LayerEnum = LayerEnum.ocr_confidence

openpecha/formatters/formatter.py

@@ -3,12 +3,13 @@
 from pathlib import Path
 from uuid import uuid4
 
-from .. import config
-from .layers import *
-from .layers import AnnType, _attr_names
-
+from openpecha import config
+from openpecha.core.layer import LayerEnum
+from openpecha.formatters.layers import *
+from openpecha.formatters.layers import _attr_names
 from openpecha.utils import dump_yaml, load_yaml
 
+
 class Global2LocalId:
     """Map global id of annotation in a layer to local id of a layer."""
 
@@ -249,7 +250,7 @@ def update_layer(self, layer, anns, vol_id):
 
     def _get_vol_layers(self, layers):
         for layer_name in layers:
-            if layer_name in [AnnType.topic, AnnType.sub_topic]:
+            if layer_name in [LayerEnum.topic, LayerEnum.sub_topic]:
                 continue
             layers[layer_name] = _name(layer_name, layers[layer_name])
         return zip(*layers.values())
@@ -260,7 +261,7 @@ def format_layer(self, layers):
 
         # filter cross vols layers from layers
         cross_vols_layers = {}
-        for cross_ann_name in [AnnType.topic, AnnType.sub_topic]:
+        for cross_ann_name in [LayerEnum.topic, LayerEnum.sub_topic]:
             cross_vols_layers[cross_ann_name] = layers[cross_ann_name]
             del layers[cross_ann_name]
 
@@ -282,12 +283,13 @@ def format_layer(self, layers):
 
             yield result, vol_id
 
-        if AnnType.topic not in old_layers:
+        if LayerEnum.topic not in old_layers:
             # Create Index layer
             Index_layer = Layer(self.get_unique_id(), "index")
             # loop over each topic
             for topics, sub_topics in zip(
-                cross_vols_layers[AnnType.topic], cross_vols_layers[AnnType.sub_topic]
+                cross_vols_layers[LayerEnum.topic],
+                cross_vols_layers[LayerEnum.sub_topic],
             ):
                 if topics:
                     Topic = deepcopy(Text)

openpecha/formatters/hfml.py

@@ -5,15 +5,14 @@
 HFML (Human Friendly Markup Language) contains tagset used for structuring and annotating the text.
 """
 import re
-from json import encoder
 from pathlib import Path
 
 import yaml
 
-from ..utils import Vol2FnManager, dump_yaml, load_yaml
-from .formatter import BaseFormatter
-from .layers import *
-from .layers import AnnType, _attr_names
+from openpecha.utils import Vol2FnManager, dump_yaml, load_yaml
+from openpecha.formatters.formatter import BaseFormatter
+from openpecha.formatters.layers import *
+from openpecha.formatters.layers import LayerEnum, _attr_names
 
 
 class HFMLFormatter(BaseFormatter):
@@ -103,7 +102,7 @@ def get_input(self, input_path):
             yield self.text_preprocess(fn.read_text()), fn.name, fns_len
 
     def total_pattern(self, pat_list, annotated_line):
-        """ It calculates the length of all the annotation detected in a line.
+        """It calculates the length of all the annotation detected in a line.
 
         Args:
             pat_list (dict): It contains all the annotation's regex pattern as value and name of annotation as key.
@@ -193,7 +192,7 @@ def total_pattern(self, pat_list, annotated_line):
         return total_length
 
     def merge(self, start_list, end_list):
-        """ It merges two list.
+        """It merges two list.
         The starting  and ending of annotation(citaion,yigchung,sabche and tsawa) are stored in two list.
         Merging these two list will generate a list in which both starting and ending of an annotation together in a tuple.
         It is applicable only if the annotaions are not cross volume.
@@ -217,7 +216,7 @@ def merge(self, start_list, end_list):
         return result
 
     def search_before(self, ann, pat_list, line):
-        """ It calculates the length of annotation detected in a given line before a given annotation.
+        """It calculates the length of annotation detected in a given line before a given annotation.
         Args:
             ann (match object): It is a match object of the annotation of which we want to calculate
                                 the length of any annotation detected before it.
@@ -319,7 +318,7 @@ def search_before(self, ann, pat_list, line):
         return length_before
 
     def base_extract(self, pat_list, annotated_line):
-        """ It extract the base text from annotated text.
+        """It extract the base text from annotated text.
         Args:
             pat_list (dict): It contains all the annotation's regex pattern as value and name of annotation as key.
             annotated_line (str): It contains the annotated line from which we want to extract the base text.
@@ -947,29 +946,29 @@ def get_result(self):
                 self.sub_topic = self.sub_topic[1:]
         self.sub_topic = self.__final_sub_topic(self.sub_topic)
         result = {
-            AnnType.book_title: self.book_title,
-            AnnType.book_number: self.book_number,
-            AnnType.author: self.author,
-            AnnType.poti_title: self.poti_title,
-            AnnType.chapter: self.chapter_title,
-            AnnType.citation: self.citation_pattern,
-            AnnType.pagination: self.page,  # page variable format (start_index,end_index,pg_Info,pg_ann)
-            AnnType.topic: self.topic_id,
-            AnnType.sub_topic: self.sub_topic,
-            AnnType.sabche: self.sabche_pattern,
-            AnnType.tsawa: self.tsawa_pattern,
-            AnnType.yigchung: self.yigchung_pattern,
-            AnnType.correction: self.error_id,
-            AnnType.error_candidate: self.abs_er_id,
-            AnnType.peydurma: self.notes_id,
-            AnnType.archaic: self.archaic_word_id,
-            AnnType.durchen: self.durchen_pattern,
+            LayerEnum.book_title: self.book_title,
+            LayerEnum.book_number: self.book_number,
+            LayerEnum.author: self.author,
+            LayerEnum.poti_title: self.poti_title,
+            LayerEnum.chapter: self.chapter_title,
+            LayerEnum.citation: self.citation_pattern,
+            LayerEnum.pagination: self.page,  # page variable format (start_index,end_index,pg_Info,pg_ann)
+            LayerEnum.topic: self.topic_id,
+            LayerEnum.sub_topic: self.sub_topic,
+            LayerEnum.sabche: self.sabche_pattern,
+            LayerEnum.tsawa: self.tsawa_pattern,
+            LayerEnum.yigchung: self.yigchung_pattern,
+            LayerEnum.correction: self.error_id,
+            LayerEnum.error_candidate: self.abs_er_id,
+            LayerEnum.peydurma: self.notes_id,
+            LayerEnum.archaic: self.archaic_word_id,
+            LayerEnum.durchen: self.durchen_pattern,
         }
 
         return result
 
     def __final_sub_topic(self, sub_topics):
-        """ It include all the sub topic belonging in one topic in a list.
+        """It include all the sub topic belonging in one topic in a list.
 
         Args:
             sub_topic (list): It contains all the sub topic annotation's starting and ending index along with sub-topic info.

openpecha/formatters/layers.py

@@ -2,7 +2,6 @@
 This module contains format variable for all the annotations
 """
 
-from collections import namedtuple
 from enum import Enum
 
 __all__ = [
@@ -31,7 +30,7 @@
 ]
 
 
-class AnnType(Enum):
+class LayerEnum(Enum):
     book_title = "BookTitle"
     sub_title = "SubTitle"
     book_number = "BookNumber"
@@ -55,6 +54,7 @@ class AnnType(Enum):
     durchen = "Durchen"
     footnote = "Footnote"
 
+
 class _attr_names:
     # Layer
     ID = "id"  # Uique id for annotation of specific Pecha or Abstract work. type: str

openpecha/formatters/pedurma.py

@@ -1,10 +1,10 @@
 import re
 from pathlib import Path
 
-from ..utils import Vol2FnManager
-from .formatter import BaseFormatter
-from .layers import *
-from .layers import AnnType, _attr_names
+from openpecha.core.layer import LayerEnum
+from openpecha.formatters.formatter import BaseFormatter
+from openpecha.formatters.layers import *
+from openpecha.utils import Vol2FnManager
 
 
 class PedurmaFormatter(BaseFormatter):
@@ -154,10 +154,10 @@ def build_layers(self, text):
 
     def get_result(self):
         result = {
-            AnnType.topic: [],
-            AnnType.sub_topic: [],
-            AnnType.pagination: self.page,
-            AnnType.pedurma_note: self.durchen,
+            LayerEnum.topic: [],
+            LayerEnum.sub_topic: [],
+            LayerEnum.pagination: self.page,
+            LayerEnum.pedurma_note: self.durchen,
         }
         return result
 

openpecha/formatters/tsadra.py

@@ -1,19 +1,16 @@
 import os
-from copy import deepcopy
 from functools import partial
 from pathlib import Path
-from re import sub
 
 from bs4 import BeautifulSoup
 
-from .formatter import BaseFormatter
-from .layers import *
-from .layers import AnnType
+from openpecha.formatters.formatter import BaseFormatter
+from openpecha.formatters.layers import *
+from openpecha.formatters.layers import LayerEnum
 
 
 class TsadraTemplate:
-    """Content tsadra template components.
-    """
+    """Content tsadra template components."""
 
     author = [
         "credits-page_front-page---text-author",
@@ -450,20 +447,20 @@ def get_result(self):
         """
         self.get_footnote_ann()
         result = {
-            AnnType.book_title: [self.book_title],
-            AnnType.sub_title: [self.sub_title],
-            AnnType.book_number: [self.book_number],
-            AnnType.poti_title: [self.poti_title],
-            AnnType.author: [self.author],
-            AnnType.chapter: [self.chapter],
-            AnnType.topic: [self.topic],
-            AnnType.sub_topic: [self.sub_topic],
-            AnnType.pagination: [self.pagination],
-            AnnType.tsawa: [self.root_text],
-            AnnType.citation: [self.citation],
-            AnnType.sabche: [self.sabche],
-            AnnType.yigchung: [self.yigchung],
-            AnnType.footnote: [self.footnote],
+            LayerEnum.book_title: [self.book_title],
+            LayerEnum.sub_title: [self.sub_title],
+            LayerEnum.book_number: [self.book_number],
+            LayerEnum.poti_title: [self.poti_title],
+            LayerEnum.author: [self.author],
+            LayerEnum.chapter: [self.chapter],
+            LayerEnum.topic: [self.topic],
+            LayerEnum.sub_topic: [self.sub_topic],
+            LayerEnum.pagination: [self.pagination],
+            LayerEnum.tsawa: [self.root_text],
+            LayerEnum.citation: [self.citation],
+            LayerEnum.sabche: [self.sabche],
+            LayerEnum.yigchung: [self.yigchung],
+            LayerEnum.footnote: [self.footnote],
         }
         return result