python - 使用Python按 block 解析文件并从每个 block 中提取信息

Question

我正在尝试解析 vrml 文件中的一些文本 block 。具体来说，我对 IndexedFaceSets 中包含的信息感兴趣，它表示由其坐标点(字段点)和点之间的连接性(字段 coordIndex)定义的一系列三角形。

我已经成功创建了一个解析单个indexedFaceSet(第一个)文本的函数，但我无法理解如何修改代码，因此我可以存储以下列表[translate,verts每个 IndexedFaceSet 的 ,facets,normals]。

我的职能是:

def extractDataFromVRML(root):
    #Lists to be populated
    translate=[]
    verts=[]
    facets=[]
    normals=[]
    #Parsing the vrml file
    f=open(root+'.wrl')
    while 1:# skip through initial stuff
      linney=str.split(f.readline())
    # print linney
      if len(linney) == 4:
        if linney[0] == 'translation': #Not shown in th vrml example
          transx = float(linney[1])
          transy = float(linney[2])
          transz = float(linney[3])
          t=[transx,transy,transz]
          translate.append(t)
      if linney == ['point', '[']:
        break
    #print 'Reading vertex coordinates.'
    while 1:
      xyz = f.readline()
      i = str.find(xyz,',')
      if i < 0:    # end of vertex coordinates
        break
      verts.append(xyz[:i]) # building a list of xyz strings
    print ('We have',len(verts)-1,'vertices.')
    #for v in verts: print v
    print ('Reading triangles.')
    while 1:
      linney=f.readline()
      if linney == '}\n':
        break     # end of file
      abc = str.split(str.replace(linney,',',' ')) # l of vertex ids
      if len(abc) < 3:
        continue   # separation between groups of triangles
      # look up a vertex in the list to generate a triangle tuple
      xyz = str.split(verts[int(abc[0])])
      p1=[float(xyz[0]),float(xyz[1]),float(xyz[2])]     
      xyz = str.split(verts[int(abc[1])])
      p2=[float(xyz[0]),float(xyz[1]),float(xyz[2])]     
      xyz = str.split(verts[int(abc[2])])
      p3=[float(xyz[0]),float(xyz[1]),float(xyz[2])]     
      tri=[p1,p2,p3]
      facets.append(tri)
      #n=getNormals(p1[0],p1[1],p1[2],p2[0],p2[1],p2[2],p3[0],p3[1],p3[2])
      #normals.append(n)
    print ('END')
    return [translate,verts,facets,normals]

vrml中的立方体示例如下:

#VRML V2.0 utf8

WorldInfo {
    info [ "File created using CATIA" ]
}
NavigationInfo {
    type [ "EXAMINE" , "WALK" , "FLY" ]
}
Background {
    skyColor [ 1 1 1 ]
}
Viewpoint {
    position      0.411502 0.183945 0.216403
    orientation   0.326678 0.502925 0.800218 2.185925
    fieldOfView   0.471225
    description   "Main Viewpoint"
}
Viewpoint {
    position      0.288675 0.288675 0.288675
    orientation   0.187053 0.451587 0.872399 2.448076
    fieldOfView   0.471225
    description   "Iso View"
}
Viewpoint {
    position      0.500000 0.000000 0.000000
    orientation   0.577350 0.577350 0.577350 2.094395
    fieldOfView   0.471225
    description   "Front View"
}
Viewpoint {
    position      -0.500000 0.000000 0.000000
    orientation   0.577350 -0.577350 -0.577350 2.094395
    fieldOfView   0.471225
    description   "Back View"
}
Viewpoint {
    position      0.000000 -0.500000 0.000000
    orientation   1.000000 -0.000173 0.000173 1.570796
    fieldOfView   0.471225
    description   "Left View"
}
Viewpoint {
    position      0.000000 0.500000 0.000000
    orientation   -0.000122 -0.707107 -0.707107 3.141348
    fieldOfView   0.471225
    description   "Right View"
}
Viewpoint {
    position      0.000000 0.000000 0.500000
    orientation   0.000000 0.000000 1.000000 1.570796
    fieldOfView   0.471225
    description   "Top View"
}
Viewpoint {
    position      0.000000 0.000000 -0.500000
    orientation   0.707107 0.707107 0.000000 3.141593
    fieldOfView   0.471225
    description   "Bottom View"
}
Transform {
    scale         0.001 0.001 0.001
    children [
Group {
    children [
Group {
    children [
DEF _000000002346A9A0 Group {
    children [
    ]
}
    ]
}
Group {
    children [
DEF _0000000023470B20 Group {
    children [
    ]
}
    ]
}
Group {
    children [
DEF _00000000234700D0 Group {
    children [
    ]
}
    ]
}
Group {
    children [
Group {
    children [
DEF _0000000020D0F390 Group {
    children [
Shape {
appearance Appearance {
    material DEF _material0 Material {
        diffuseColor  0.823529 0.823529 1
    }
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         0 50 50,
         50 50 50,
         50 0 50,
         0 0 50,
        ]
    }
coordIndex [
 3,2,0,-1,
 2,1,0,-1,
]

}
}
Shape {
appearance Appearance {
material USE _material0
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         0 50 0,
         50 50 0,
         50 0 0,
         0 0 0,
        ]
    }
coordIndex [
 3,0,2,-1,
 0,1,2,-1,
]

}
}
Shape {
appearance Appearance {
material USE _material0
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         0 0 50,
         0 0 0,
         0 50 0,
         0 50 50,
        ]
    }
coordIndex [
 2,1,3,-1,
 1,0,3,-1,
]

}
}
Shape {
appearance Appearance {
material USE _material0
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         0 50 50,
         0 50 0,
         50 50 0,
         50 50 50,
        ]
    }
coordIndex [
 2,1,3,-1,
 1,0,3,-1,
]

}
}
Shape {
appearance Appearance {
material USE _material0
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         50 50 50,
         50 50 0,
         50 0 0,
         50 0 50,
        ]
    }
coordIndex [
 2,1,3,-1,
 1,0,3,-1,
]

}
}
Shape {
appearance Appearance {
material USE _material0
}
geometry IndexedFaceSet {
solid FALSE
coord Coordinate {
    point   [
         50 0 50,
         50 0 0,
         0 0 0,
         0 0 50,
        ]
    }
coordIndex [
 2,1,3,-1,
 1,0,3,-1,
]

}
}
    ]
}
    ]
}
    ]
}
    ]
}
    ]
}

Answer 1

这是一个不平凡的解析问题。如果能找到一些Python包来解析那就最好了。这是我的方法:逐行扫描文件。如果我看到一些我理解的内容，则将剩余的行传递给该 block 的解析器。例如，我有解析器来解析以“geometry IndexedFaceSet”行开头的 block 。

import itertools
import json
import logging
from pprint import pprint
import os

# For the next line, use logging.WARN to turn off debug print, use
# logging.DEBUG to turn on
logging.basicConfig(level=os.getenv('LOGLEVEL', logging.WARN))
logger = logging.getLogger(__name__)


def skip_pass(marker, lines):
    """
    Skip until reach the line which contains the marker, then also skip
    the marker line
    """
    result = itertools.dropwhile(
        lambda line: marker not in line,  # Condition
        lines)                            # The lines
    next(result)                          # skip pass the marker
    return result

def take(marker, lines):
    """
    Take and return those lines which contains a marker
    """
    result = itertools.takewhile(
        lambda line: marker in line,      # Condition
        lines)                            # The lines
    return result

def parse_indexed_face_set(translate, lines):
    """
    Parse one block of 'geometry IndexedFaceSet'
    """
    # lines = skip_pass('geometry IndexedFaceSet', lines)

    # Parse the "point" structure
    lines = skip_pass('point', lines)
    point_lines = take(',', lines)
    verts = [[float(token) for token in line.strip(',\n').split()] for line in point_lines]
    logger.debug('verts: %r', verts)

    # parse the coordIndex structure
    lines = skip_pass('coordIndex', lines)
    coor_lines = take(',', lines)
    coord_index = [tuple(int(token) for token in line.strip(',\n').split(',')) for line in coor_lines]
    logger.debug('coord_index: %r', coord_index)

    facets = [[verts[i] for i in indices[:3]] for indices in coord_index]
    logger.debug('facets: %r', facets)

    return dict(vert=verts, facets=facets, translate=translate, normals=[])

def parse_translate(line):
    """
    Given a line such as: "translate 5 6 7", return [5.0, 6.0, 7.0]
    """
    translate = [float(x) for x in line.split()[1:4]]
    return translate

def extractDataFromVRML(root):
    indexed_face_sets = []
    translate = []
    with open(root + '.wrl') as infile:
        for line in infile:
            if 'geometry IndexedFaceSet' in line:
                a_set = parse_indexed_face_set(translate=translate, lines=infile)
                indexed_face_sets.append(a_set)
            elif 'translation' in line and line.split()[0] == 'translation':
                translate = parse_translate(line)

    return indexed_face_sets


# main
indexed_face_sets = extractDataFromVRML('root')
for a_set in indexed_face_sets:
    print('vert:', a_set['vert'])
    print('facets:', a_set['facets'])
    print('---')

输出

vert: [[0.0, 50.0, 50.0], [50.0, 50.0, 50.0], [50.0, 0.0, 50.0], [0.0, 0.0, 50.0]]
facets: [[[0.0, 0.0, 50.0], [50.0, 0.0, 50.0], [0.0, 50.0, 50.0]], [[50.0, 0.0, 50.0], [50.0, 50.0, 50.0], [0.0, 50.0, 50.0]]]
---
vert: [[0.0, 50.0, 0.0], [50.0, 50.0, 0.0], [50.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
facets: [[[0.0, 0.0, 0.0], [0.0, 50.0, 0.0], [50.0, 0.0, 0.0]], [[0.0, 50.0, 0.0], [50.0, 50.0, 0.0], [50.0, 0.0, 0.0]]]
---
vert: [[0.0, 0.0, 50.0], [0.0, 0.0, 0.0], [0.0, 50.0, 0.0], [0.0, 50.0, 50.0]]
facets: [[[0.0, 50.0, 0.0], [0.0, 0.0, 0.0], [0.0, 50.0, 50.0]], [[0.0, 0.0, 0.0], [0.0, 0.0, 50.0], [0.0, 50.0, 50.0]]]
---
vert: [[0.0, 50.0, 50.0], [0.0, 50.0, 0.0], [50.0, 50.0, 0.0], [50.0, 50.0, 50.0]]
facets: [[[50.0, 50.0, 0.0], [0.0, 50.0, 0.0], [50.0, 50.0, 50.0]], [[0.0, 50.0, 0.0], [0.0, 50.0, 50.0], [50.0, 50.0, 50.0]]]
---
vert: [[50.0, 50.0, 50.0], [50.0, 50.0, 0.0], [50.0, 0.0, 0.0], [50.0, 0.0, 50.0]]
facets: [[[50.0, 0.0, 0.0], [50.0, 50.0, 0.0], [50.0, 0.0, 50.0]], [[50.0, 50.0, 0.0], [50.0, 50.0, 50.0], [50.0, 0.0, 50.0]]]
---
vert: [[50.0, 0.0, 50.0], [50.0, 0.0, 0.0], [0.0, 0.0, 0.0], [0.0, 0.0, 50.0]]
facets: [[[0.0, 0.0, 0.0], [50.0, 0.0, 0.0], [0.0, 0.0, 50.0]], [[50.0, 0.0, 0.0], [50.0, 0.0, 50.0], [0.0, 0.0, 50.0]]]
---

注释

• 在开发过程中，我经常需要打印一些值以进行调试。为此，我使用从 logging 库创建的记录器对象
• 我使用 itertools.takewhile() 和 itertools.dropwhile() 函数来简化一些任务