可以拆分列 value 由 / 分隔符以获取路径的所有部分。然后使用 transform 函数，可以使用 slice 以及 array_join 功能：

from pyspark.sql import functions as F

df1 = df.withColumn("value", F.split(F.col("value"), "/")) \
    .selectExpr("""
      explode(
           transform(value, 
                     (x, i) -> struct(i+1 as rn, array_join(slice(value, 1, i+1), '/') ||
                                      IF(i+1 < size(value), '/', '') as path)
                     )
       ) as paths
    """).select("paths.*")

df1.show(truncate=False)

# +---+---------------------------------------------------------+

# |rn |path                                                     |

# +---+---------------------------------------------------------+

# |1  |ParentFolder/                                            |

# |2  |ParentFolder/Folder1/                                    |

# |3  |ParentFolder/Folder1/Folder2/                            |

# |4  |ParentFolder/Folder1/Folder2/Folder3/                    |

# |5  |ParentFolder/Folder1/Folder2/Folder3/Folder4/            |

# |6  |ParentFolder/Folder1/Folder2/Folder3/Folder4/TestFile.txt|

# +---+---------------------------------------------------------+

对于spark<2.4，可以这样使用udf：

import os
from pyspark.sql import functions as F
from pyspark.sql.types import ArrayType, StringType

def get_all_paths(path: str):
    paths = [path]
    for _ in range(path.count("/")):
        path, base = os.path.split(path)
        paths.append(path + "/")

    return list(reversed(paths))

decompose_path = F.udf(get_all_paths, ArrayType(StringType()))

df1 = df.select(F.explode(decompose_path(F.col("value"))).alias("paths"))

你可以用 substring_index 具体如下：

df2 = df.selectExpr("""
    explode(
        transform(
            sequence(1, size(split(col, '/'))),
            (x, i) -> case when i = size(split(col, '/')) - 1
                           then col
                           else substring_index(col, '/', x) || '/'
                           end
        )
    ) as col
""")

df2.show(20,0)
+---------------------------------------------------------+
|col                                                      |
+---------------------------------------------------------+
|ParentFolder/                                            |
|ParentFolder/Folder1/                                    |
|ParentFolder/Folder1/Folder2/                            |
|ParentFolder/Folder1/Folder2/Folder3/                    |
|ParentFolder/Folder1/Folder2/Folder3/Folder4/            |
|ParentFolder/Folder1/Folder2/Folder3/Folder4/TestFile.txt|
+---------------------------------------------------------+