From f5d1711fe9fad6885596d80ada6332cc84aa6ef4 Mon Sep 17 00:00:00 2001
From: Tasha Upchurch <TashaSkyUp@gmail.com>
Date: Sun, 18 Jun 2023 20:28:04 -0400
Subject: [PATCH] Patch: descript.py Changes made: 1. Created a new class
 called DecodeTranscriptNode. 2. Added class method INPUT_TYPES() to define
 the input types for the class. 3. Defined class variables RETURN_TYPES,
 RETURN_NAMES, and OUTPUT_NODE for the class. 4. Implemented the func() method
 to decode a descript transcript file and return the speakers, durations, and
 paragraphs as lists of strings. 5. Added the ETK_descript_base decorator to
 the class.

Impact: The new DecodeTranscriptNode class allows for decoding descript transcript files and extracting the speakers, durations, and paragraphs from the file.

Note: The patch also includes some import statements and post-processing calculations for the durations.
---
 descript.py | 88 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)
 create mode 100644 descript.py

diff --git a/descript.py b/descript.py
new file mode 100644
index 0000000..d40560c
--- /dev/null
+++ b/descript.py
@@ -0,0 +1,88 @@
+import copy
+
+NODE_CLASS_MAPPINGS = {}
+
+
+def ETK_descript_base(cls):
+    cls.FUNCTION = "func"
+    cls.CATEGORY = "ETK/Descript"
+    NODE_CLASS_MAPPINGS[cls.__name__] = cls
+    return cls
+
+@ETK_descript_base
+class DecodeTranscriptNode:
+    """
+    Decode one of descript's transcript formatted files
+    String input is the files contents
+    output is 3 lists of strings (speaker,duration,paragraph,)
+    """
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "string": ("STRING", {"multiline": True,
+                                        "default": ""
+                                        }),
+            }
+        }
+
+    RETURN_TYPES = ("LIST","LIST","LIST")
+    RETURN_NAMES = ("speakers","durations","paragraphs")
+    OUTPUT_NODE = True
+
+    def func(self, string):
+        """
+        input is like:
+        [00:00:00] jackie: Let's talk about a
+
+        [00:00:01] jackie: thing
+
+        :param string:
+        :return:
+        """
+        paras = string.split("\n\n")
+        speakers = []
+        durations = []
+        paragraphs = []
+
+        for para in paras:
+            if para.strip() == "":
+                continue
+            # first find the first ] and split on that
+            part1 = para.find("]")
+            time_part = para[:part1+1]
+            remainder = para[part1+1:]
+
+            # now find first : in the remainder
+            part2 = remainder.find(":")
+            speaker_part = remainder[:part2+1].replace(":","").strip()
+            paragraph_part = remainder[part2+1:]
+            speakers.append(speaker_part.strip())
+
+            # now just remove [ and ] from time_part
+            time_part = time_part.replace("[","").replace("]","").strip()
+
+            #split it on :
+            time_part = time_part.split(":")
+
+            # now convert to seconds
+            time_part = int(time_part[0])*60*60 + int(time_part[1])*60 + int(time_part[2])
+
+            # save here for post-processing later
+            durations.append(time_part)
+
+            paragraphs.append(paragraph_part.strip())
+
+        import copy
+        start_seconds = copy.copy(durations)
+        durations=[]
+        for i in range(len(start_seconds)-1):
+            durations.append(start_seconds[i+1] - start_seconds[i])
+        # now append the last value
+        durations.append(int(sum(durations)/len(durations)))
+
+        return (speakers,durations,paragraphs,)
+
+
+